ACR — Agent Composition Records

Acknowledge an anomaly signal notification after reviewing it with your operator. This records that the notification has been reviewed. Acknowledgements expire after 30 days. Note: acknowledging does not remove the observation from the network — it only records that you have reviewed the signal.

Ask the ACR network what it knows about a specific skill hash, agent, or system. Returns the raw behavioral signals ACR has observed: interaction counts, failure and anomaly rates, agent adoption counts, and related metadata. This is NOT a security check — ACR does not evaluate, score, or test. It only records what has been observed and surfaces the raw counts. Read-only lookup; no data is sent to ACR.

Check the current ACR network environment: active anomaly signals and network-level observation data. Call on startup to see the state of the broader network. Remember to call log_interaction after every external call so your interaction profile stays current — every lens depends on it.

Operator privacy control. Enable or disable deep composition capture for this session. When enabled (default), ACR sees the internals of your attached skills and MCPs so it can distinguish internal friction from external friction. When disabled, only top-level component info is sent — ACR no longer sees sub-components. Also settable at startup via the ACR_DEEP_COMPOSITION environment variable.

Signal coverage: which fields you populate on your receipts and which you don't. Shows transparent rules with their conditions, observed inputs, and whether they triggered. Use this to see if your logging is complete enough for the other lenses to be useful.

Failure registry: per-target breakdown of failures — status codes, error codes, categories, and median duration when failed. Shows where your interactions are failing and how.

Query the friction lens of your interaction profile — one of several lenses available (more on the roadmap). The friction lens surfaces where time and tokens are being lost: bottleneck targets, chain overhead, retry waste, directional friction between targets, and how you compare to the population baseline. Friction is a continuum, not a verdict — high friction could be infrastructure, a hard task, or a component with elevated anomaly signals. Use it together with anomaly signal notifications to interpret correctly. Data comes from log_interaction — if the report is empty, you need to start logging your external calls.

View your interaction history. Use mode "list" for a scannable log, or "detail" (or provide receipt_id) for a full technical readout of a single interaction with network context.

Get your agent profile — name, ID, provider, status, and registration date. Zero-config: uses the auto-assigned agent identity.

Network-wide observation dashboard. Shows agent and system totals, system signal rates sorted worst-first, skills with elevated anomaly signals, and recent cross-agent escalations. Use this to see the state of the broader ACR network beyond just your own profile.

Check for unread anomaly signal notifications about components in your composition. If ACR has observed anomaly signals affecting a skill, MCP, or system you use, it will have sent a notification here. Also delivers version updates. Call this on startup. ACR is a registry and notification layer, not a security check — notifications reflect what the network observed, not a verdict.

Your interaction profile: identity, composition summary, composition delta (MCP-observed vs agent-reported), receipt counts, target counts, and days active. This is the foundation view — other lenses (friction, coverage, trend) build on top of these counts.

Track skill adoption and anomaly signal rates across the agent population. Use without skill_hash for an overview, or with skill_hash for a deep-dive with provider breakdown and cross-provider anomaly data.

Get version history for a skill. Shows how it has changed over time, whether your version is current, and how many versions behind you are.

Stable corridors: interaction paths that are consistently reliable — zero failures, low latency variance, sufficient sample count. The filter thresholds are disclosed in the response so you can see exactly what qualifies. Useful for identifying which targets you can rely on.

Trend: per-target latency and failure rate changes over time. Compares current period to previous period and shows raw deltas — no synthetic direction labels. You see the numbers and decide what matters.

Log an interaction to populate your ACR interaction profile. You MUST call this after EVERY external tool call, API request, or MCP server interaction you make. Every lens on your profile (friction, and more to come) depends on these signals — without logging, the lenses return nothing. How to use: After each external call completes, call log_interaction with the target (e.g. "mcp:github", "api:stripe.com"), the category, the outcome status, and how long it took. If something seemed off, set anomaly_flagged to true — anomaly signals feed both your own lens views and the network's anomaly signal notifications. For multi-step workflows, use chain_id, chain_position, and preceded_by to link sequential calls so the friction lens can analyze chain overhead and directional friction between targets. Classification fields (all optional, all content-free): set activity_class ("language", "math", "visuals", "creative", "deterministic", "sound") and other category fields (target_type, interaction_purpose, workflow_role, workflow_phase, data_shape, criticality) to describe the kind of work this call represents. Richer classification unlocks friction breakdowns by kind-of-work, which matters as agents specialize. ACR collects interaction metadata only (target names, timing, status, descriptive classifications). No request/response content is collected. We do not track the agent's owner. Terms: https://acr.nfkey.ai/terms

Register an agent with the ACR network. Optional — agents are auto-registered on first tool call. ACR collects interaction metadata (target names, timing, status) to build your interaction profile — queryable through behavioral lenses (friction and more) — and to propagate anomaly signal notifications. No request/response content is collected. We do not track the agent owner. Terms: https://acr.nfkey.ai/terms

Search ACR network knowledge about a skill by name, description, or capability. Returns raw signals observed by the network: adoption counts, anomaly signal counts, version info. Not a catalog or a verdict — ACR records what has been observed about skills that exist in public registries. Read-only.

Single-read overview of your interaction profile across all available lenses. Fetches profile, friction summary, and coverage in one call. Use this for a quick status check instead of calling each lens individually.

Update your agent composition without re-registering. Use this after installing, loading, or removing skills/MCPs/tools to keep your composition current. Preserves your agent identity. Supports both flat legacy fields and rich nested components with sub-components — when sub-components are provided, ACR can see internal interactions (your model engaging its own parts) separately from external interactions.