# coldstart (npm · @cstart/coldstart)

Codebase memory for AI agents: an AST index plus agent-written notes that self-stale.

- Trust score: 76/100 (medium)
- Change this week: +53
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-03

## Components

- npm · `@cstart/coldstart`: 76/100 (this document), [markdown](https://verifymcp.io/servers/akashgoenka-coldstart/cstart-coldstart.md), [page](https://verifymcp.io/servers/akashgoenka-coldstart/cstart-coldstart)

## Channel facts

- Registry: `npm`
- Package: `@cstart/coldstart`
- Version: `2.2.12`
- Transport: `stdio`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-08-03.

- **Supply Chain Security**: 87/100
  - No malware found by supply-chain analysis.
  - Only part of the dependency tree could be resolved (108 of 112), so this covers what we could see, not the whole tree.
  - No install/post-install scripts declared.
  - Only part of the dependency tree could be resolved (108 of 112), so this covers what we could see, not the whole tree.
- **Provenance & Transparency**: 97/100
  - Source repository is publicly reachable at the declared URL.
  - Cryptographically verified build provenance (signed, bound to AkashGoenka/coldstart).
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 0 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 56/100
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 3384 tokens (~423/item across 8 items; 8 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 27/100
  - Stability observed for 8 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### Claude

```bash
claude mcp add akashgoenka-coldstart -- npx -y @cstart/coldstart
```

### Codex

```bash
codex mcp add akashgoenka-coldstart -- npx -y @cstart/coldstart
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "akashgoenka-coldstart": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "@cstart/coldstart"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add akashgoenka-coldstart --command npx --arg -y --arg @cstart/coldstart
```

### Hermes

```yaml
mcp_servers:
  akashgoenka-coldstart:
    command: "npx"
    args: ["-y", "@cstart/coldstart"]
```

### Other

```json
{
  "mcpServers": {
    "akashgoenka-coldstart": {
      "command": "npx",
      "args": [
        "-y",
        "@cstart/coldstart"
      ]
    }
  }
}
```

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-08-03 (score 76, +1)

No change was recorded against any check on this day. Stability & Change Management went from 23 to 27. That category is still filling its 30-day observation window: 7 days of observed history at the previous scan, 8 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-08-02 (score 75, +10)

- [security regression] Provenance: pass → unverified
- [security regression] Known CVEs: partial → unverified
- [security regression] Malware scan: pass → unverified
- [security regression] Install scripts: pass → unverified
- [security] Stability: Stability not yet verified: we do not have a sandbox capture of the MCP schema this version of the package serves yet.
- [security] The attested source repository moved: AkashGoenka/coldstart
- [functional regression] Schema quality: 2710 → 3384
- [functional regression] Capabilities: pass → unverified
- [functional regression] License: pass → unverified
- [functional regression] Tool coverage: 100 → unverified
- [functional regression] Dependency health: partial → unverified
- [functional regression] Maintenance: pass → unverified
- [functional improvement] Stability: unverified → 0.23
- [functional improvement] Schema quality: unverified → excellent
- [functional] Licence: MIT
- [functional] Package version: 2.2.8 → 2.2.12

### 2026-08-01 (score 65, +43)

- [security improvement] Malware scan: unverified → pass
- [security improvement] Install scripts: unverified → pass
- [security improvement] Provenance: unverified → pass
- [security improvement] Known CVEs: unverified → partial
- [security] The attested source repository moved: AkashGoenka/coldstart
- [functional improvement] License: unverified → pass
- [functional improvement] Dependency health: unverified → partial
- [functional improvement] Maintenance: unverified → pass
- [functional] Licence: MIT

### 2026-07-31 (score 22, −1)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-30 (score 23, +15)

- [functional regression] Dependency health: partial → unverified
- [functional improvement] Tool coverage: unverified → 100

### 2026-07-28 (score 8, −15)

- [functional regression] Tool coverage: 100 → unverified
- [functional improvement] Dependency health: unverified → partial
- [functional] First check of Schema quality: unverified

### 2026-07-27 (score 23)

First indexed and scored.

## MCP tools (8)

### `find` (~464 tokens)

Locate the files relevant to a task. Pass `query` = EVERY salient identifier from the task (symbol names, domain nouns, the rare token you half-remember) — not one distilled keyword. Recall is bounded by the terms you give: a one-token query cannot out-rank lookalikes, so over-supply rather than under-supply. Reach for find BEFORE Read/Grep/Glob.

HOW IT WORKS: find greps every term across the repo body AND matches declared names (filenames, path segments, exported symbols), then ranks files by DISTINCT-TERM COVERAGE — the file that covers MORE of your query rises above its lookalikes. This catches body-level matches (nested defs, dynamic refs, string literals) that a declared-name index misses.

OUTPUT: a ranked page. Top files get an inline preview — their indexed symbols (with line ranges) plus the body lines where your rare terms CLUSTER (def/class/assignment lines first), so you often answer WITHOUT a follow-up Read. Lower-ranked files list as bare paths. Prose/doc and stylesheet matches are partitioned into secondary lists so they do not crowd out source. Related files (sharing a rare identifier with a top hit, no import edge between them) are surfaced as first-class neighbors.

NAMING: case- and separator-insensitive (`LoadStaging` ≡ `load_staging`). It does NOT expand synonyms or plurals for you — that is your job: if the concept could be named two ways, pass both tokens.

AFTER THE RESULT:
1\. A path + its inline symbols/preview answer the question → done, no Read needed.
2\. Path looks right but you need shape/usage → `gs` on it (symbols + imports + per-symbol callers + importers in one shot).
3\. "no indexed file contains any of [...]" → those identifiers do not exist in the repo; reformulate or grep for a phrase/regex find cannot index. Do not grep spelling variants of a token find already reported absent.

Input parameters:

- `query` (string, required): Space-separated identifiers for the thing you are looking for — pass every salient token from the task, not one keyword. camelCase/snake_case both accepted. More discriminating tokens = sharper ranki…

### `gs` (~939 tokens)

Drill into a known file. Returns these sections as compact text:
\- Symbols — top-level + per-class methods (name, kind, line range, extends/implements). With cross-file callers attached per exported symbol (inline if 1 caller; newline-per-caller block if ≥2). For huge files (>20 symbols, no `match`), symbols are reordered by caller count (most-used first) and truncated to top 15.
\- Imports — 1-hop internal outbound dependencies (library imports stripped).
\- Importers — 1-hop reverse: files in this repo that import this one. With `match`, additionally lists EVERY indexed file (importer or not, any language) whose CONTENT references the matched term even when its filename does not (a registry, admin, or config file using the symbol — or a frontend file referencing a backend name). That subsection IS the complete "who uses <symbol>" answer: it is exhaustive over indexed content, so a subsystem absent from it does NOT use the symbol — do not grep to enumerate or re-verify use-sites, and do not keep hunting in subsystems the section rules out.
\- Related — files sharing rare identifier/string-literal tokens with this file (with `match`: with the matched symbols' code region), shown only when NO import edge connects them. These are name-reference relations the import graph cannot see — Django migrations↔models, config-by-name registration, cross-language (JS↔Python) pairs. Treat them as first-class neighbors: the shared token shown is the reason they are related.
Use this AFTER find surfaces a candidate file. This is the right tool for "who uses this file" / "who calls this symbol" — no separate call needed.

\`view` controls which sections you get (default `full` = all four). `symbols`, `imports`, `importers`, `callers` each return one section in isolation when you want a byte-light answer.

For god-files (large classes, large routers, large config modules), pass `match` to filter symbols/imports/importers/callers to one area — e.g. `match: "auth"` or `match: "/^handle/"`…

Input parameters:

- `file_path` (string, required): Relative path to the file (e.g. "src/auth/service.ts"). Suffix matches are accepted.
- `match` (string): Filter all sections by name. Substring (case-insensitive) by default; use `|` to OR substrings (`match: "resource|tile"`); wrap in slashes for regex (`match: "/^handle/"`). Use this on large/god-file…
- `symbol` (string): Deliver the BODY of the named symbol(s) inline, sliced from their indexed line range — so you read a method WITHOUT a Read at a guessed offset. Comma/pipe-separate names (`serialize,restore_state`).…
- `view` (string): Which sections to return. Default "full" = symbols (with inline callers) + imports + importers. Use one of the narrower views to halve or quarter the output when you know what you need: "symbols" (sh…

### `kb_search` (~227 tokens)

Search the repo's NOTEBOOK — durable notes past agents wrote after finishing tasks here (file purposes, cross-file flows, traps/lessons, established absences). Try this BEFORE find when the task might have been seen before: a hit can answer outright or point straight at the right files, skipping a search. Pass plain task words (symptoms work: "logout loop after refresh"), symbol names, or file names.

Results are inlined in full with a freshness stamp computed against the CURRENT code: [fresh] = the cited file is byte-identical to when the note was verified; [evidence changed: <path>] = that file drifted since — re-verify before relying on it (and correct the note if it proved wrong: `coldstart kb write`). Absence notes ("there is no X") are re-checked live. No hits or an empty notebook → fall through to find, no tax.

Input parameters:

- `query` (string, required): Plain task words, symptoms, symbol names, or file names. Same over-supply rule as find: pass every salient token.

### `kb_lookup` (~256 tokens)

Read everything the NOTEBOOK knows at ONE exact address — the file you are about to edit. Address-keyed, not concept-keyed: unlike kb_search (fuzzy, ranked), this filters notes by exact anchor path, so it is exhaustive at that path. Returns the file note's facets, every cross-file flow that passes THROUGH this file, and lessons/absences anchored here — each with a live freshness stamp against the current code.

Reach for this the moment you have DECIDED on a file and are about to modify it: it surfaces the flow you might break, the absence you are about to violate, the rationale for the code's shape. A clean result ("nothing known here") is itself a positive signal — proceed. Anything marked [evidence changed: <path>] drifted since it was verified; re-verify before relying on it, and correct the note with kb_write if it proved wrong. Pass an optional `symbol` to narrow to one top-level symbol at that path.

Input parameters:

- `path` (string, required): Exact repo-relative path of the file (e.g. "src/auth/service.ts").
- `symbol` (string): Optional top-level symbol name to narrow the lookup to notes anchored at that symbol.

### `kb_write` (~772 tokens)

Save or correct a NOTEBOOK note after finishing real work here — you have the files in context, so no future agent is better placed to record what you learned. Write a file note (what a file is for), a flow note (how a task spans files), or an absence lesson (a confirmed "there is no X"). Also the tool to FIX or RETRACT a note you used that proved wrong (`op: "put"` replaces, `op: "retract"` removes).

TWO-PHASE reuse gate: a flow/lesson `spec` sent WITHOUT an `id` first searches the notebook for the same concept. If plausible matches exist, kb_write returns `{status:"candidates", candidates:[...]}` INSTEAD of writing — re-call with `into: "<id>"` to merge into an existing note, or `is_new: true` to declare a genuinely new one. This makes note identity reliable (matching, not guessing an exact title). File notes skip the gate (id derives from the path).

The `spec` shape: `type` ("file"|"flow"|"lesson", or sugar "file-hub"/"file-single"), `title`, `summary`, `anchors` ([{path, symbols?}] — the addresses the note is about, which drive freshness), plus type-specific fields (file: facets/character; flow: steps/verified; lesson: kind:"absence"/scope/body). Call with NO arguments to get the full spec guide.

REQUIRED for the note to be findable at all — file-single: identityAliases + anchors[].symbols; file-hub: identityAliases + facets[].symbol; flow: identityAliases + steps + verified; lesson: scope.terms. A note missing these is written but unreachable: identityAliases are the only STABLE search surface besides the exact title (incidentAliases are optional — symptom words for a write that describes one, replaced by the next such write, never required), and anchor symbols are the only channel that answers a query typed as an identifier.

This tool WRITES to the repo notebook; it never commits to git — publishing notes is a human-only step (`coldstart kb commit`).

Input parameters:

- `into` (string): Phase-2 answer: merge this write into the existing note with this id (from a prior `candidates` response).
- `is_new` (boolean): Phase-2 answer: declare this a genuinely new concept, bypassing the candidate matches from a prior `candidates` response.
- `session` (string): Optional session id (given in a capture prompt). Enables the flow-evidence check: a flow whose step files this session never actually read gets a warning.
- `spec` (object): The note spec (JSON object). Fields: type, title, summary, identityAliases (stable — unions forever), incidentAliases (this write's symptom words — replaced by the next write that changes summary/bod…

### `kb_status` (~120 tokens)

Notebook overview: how many notes exist (by type: file/flow/lesson), how many are flagged stale (their anchored files drifted since verification), and how many are superseded/retracted. Pass `paths` (array of repo-relative paths) to instead list the notes anchored at each of those exact paths with their freshness state — a quick "is anything known here?" check across several files at once.

Input parameters:

- `paths` (array): Optional repo-relative paths. When given, returns per-path anchored notes + freshness instead of the whole-notebook overview.

### `kb_repair` (~170 tokens)

List the notebook notes that are WRITTEN BUT UNFINDABLE — missing the fields a note cannot be retrieved without (identityAliases, anchor symbols, a flow's verified paths). Notes written before those fields were required are correct but unreachable, and this is how they get found.

Returns a worklist, never a change: repairing is your work, because every gap needs a judgement about the code (which words a reader would search for, which symbols the note is actually about, which files you can honestly claim to have read). Fix each one with kb_write, passing the note's `id` — fields merge, so nothing already in the note is lost.

A clean notebook returns "Nothing to repair here." Run it when the user asks to repair, fix, or clean up the notebook.

### `kb_repair_aliases` (~244 tokens)

List file/flow notes whose identityAliases may no longer describe them — a DIFFERENT problem from kb_repair: that one finds notes with NO aliases at all, this one is for aliases that exist but have gone stale (a note rewritten several times can carry words that were really symptoms of an earlier write, not stable facts). Paginated 10 notes at a time.

Each entry shows the current (capped) identityAliases AND the full historical union hidden past the render cap — read both before retracting anything, because dropping a visible alias can resurface an older hidden one on the next fold. Re-read the note's code, then reconcile via kb_write (retract stale entries, re-put the rest) — never mechanically, every judgement needs the current code.

Returns "No file/flow notes to reconcile." when done. If the response includes `more`, call again with `offset` set to `more.nextOffset` for the next batch.

Input parameters:

- `limit` (number): Notes per page. Defaults to 10.
- `offset` (number): Pagination offset (0-based). Use `more.nextOffset` from the previous response to continue.

## Diagnostics

Captured diagnostic sections: Provenance, Dependencies. The full working is on the page: https://verifymcp.io/servers/akashgoenka-coldstart/cstart-coldstart#diagnostics

## Score history

- 2026-08-03: 76
- 2026-08-02: 75
- 2026-08-01: 65
- 2026-07-31: 22
- 2026-07-30: 23
- 2026-07-28: 8
- 2026-07-27: 23

## Links

- npm package: https://www.npmjs.com/package/@cstart/coldstart
- Socket report: https://socket.dev/npm/package/@cstart/coldstart
- Repository: https://github.com/AkashGoenka/coldstart
- Website: https://akashgoenka.github.io/coldstart/
- Changelog RSS feed: https://verifymcp.io/servers/akashgoenka-coldstart/cstart-coldstart/changelog.xml
- Changelog JSON feed: https://verifymcp.io/servers/akashgoenka-coldstart/cstart-coldstart/changelog.json
- HTML version of this page: https://verifymcp.io/servers/akashgoenka-coldstart/cstart-coldstart