BC agent-passport-system
Enforcement and accountability layer for AI agents. Bring your own identity (did:key, did:web, SPIFFE, OAuth, did:aps). Gateway enforcement boundary, monotonic narrowing, cascade revocation, spending controls, data lifecycle, observation governance (telemetry scopes, derivation rights, behavioral memory). Use when agents need scoped delegation, trust scoring, constraint enforcement, or cryptographic audit trails. SDK leads with the /core subpath (24 curated functions), MCP leads with APS_PROFILE=essential (25 tools covering identity, delegation, enforcement, commerce, reputation). 5,281 tests. 8 framework adapters: Stripe, Composio, IBAC/Cedar, LangChain, CrewAI, MCP, A2A, Gonka. Full surface area (107 modules, 152 MCP tools) still available under APS_PROFILE=full and the root import. SDK 6.0.1 and MCP 6.0.1 are current on npm, Python 3.0.1 on PyPI, Rust 0.3.0 on crates.io, Go v0.7.0. The 3.3.1 release added Delegated Action Evidence: bilateral pair reconciliation with five mismatch classes, verifier-side revocation observation receipts under a stated freshness contract, Merkle-rooted evidence bundles with a per-axis claim-state report (verify-bundle), spec 4.1 action_ref canonicalization validated by cross-language vectors, and jurisdiction selection records that surface pack conflicts, on top of evidentiary type safety, Wave 1 accountability, Instruction Provenance Receipt, and bilateral receipts.
As a process C 51/100 · Has gaps — weak spots: result and completion, when it triggers, inputs and preconditions
How to improve
- Shorten the description to 1024 characters.
- Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 0
✓ No critical or high findings
Files scanned: 4. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- error
description-longdescription is 1422 chars, limit 1024
Process rating: all ten parameters 51/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 17 mutating operations with no state check
- 100Tools and files. No external tools needed
- 100Steps. 26 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2290 tokens
- low 10 top-level sections: this looks like several domains in one skill
Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.
Quality signals
- +5Description has no quoted example phrases that should trigger the skill
- +4Description does not say when NOT to use the skill (false activations)
- +3Description length 1422: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +4Structure: 15 headings
- +3Step-by-step instructions: 26 items
- +4Has examples (10 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 56.