From Aegis Boundary Skill
Aegis Boundary Skill — review whether AI-agent work stays within Aegis product boundaries in what it sees, does, outputs, and claims. ADVISORY review only: it does not authorize, enforce, or produce receipts — runtime enforcement belongs to the aegis-trust SDK (LITE) and Aegis Core (FULL). Reviews whether an agent task, code change, document, or public claim preserves Aegis boundaries (SDK/Core responsibility split, LITE/FULL claim separation, honesty guardrails, never-claims, naming) and returns READY / REVIEW / STOPPED with machine-check evidence. Use when: working with aegis-trust or Aegis Core integrations; editing README, website, sales, or customer-facing claims about Aegis; changing what an AI agent is allowed to see, do, or output through Aegis; before publishing any artifact that makes claims about Aegis; or when asked "boundary review", "claim check", "境界確認", "claim parity", "can we say this publicly?". NOT for: production authorization decisions (SDK/Core runtime territory), projects unrelated to Aegis.
How this skill is triggered — by the user, by Claude, or both
Slash command
/aegis-boundary:aegis-boundaryThis skill is limited to the following tools:
The summary Claude sees in its skill listing — used to decide when to auto-load this skill
> Advisory review: does this work stay within Aegis product boundaries — in
Advisory review: does this work stay within Aegis product boundaries — in what it sees, does, outputs, and claims?
This skill does not replace the aegis-trust SDK or Aegis Core.
decision_ids.
Its output is advisory review, labeled source: aegis-boundary-skill —
never source: CORE (that label is reserved for gateway-constructed
decisions).Stay scoped to boundary review. Route other needs to the right place:
Pick every class that applies:
Resolve the script against this skill's own directory (it does not depend on the current working directory):
python3 "<skill-dir>/scripts/check_overclaims.py" <changed .md files...>
# In a Claude Code plugin this is "${CLAUDE_PLUGIN_ROOT}/skills/aegis-boundary/scripts/check_overclaims.py";
# when run from the skill directory itself, "scripts/check_overclaims.py" also works.
Scans for the three known overclaim families defined in
references/boundary_canon.md §5-A (C-1, C-2, C-3). Exit codes cap this
review's decision: any FAIL means
the final decision can never be READY. They cap nothing at runtime. Do not
reinterpret, soften, or override a machine FAIL with narrative judgment.
Known limitation: the patterns match English phrasings only. For non-English
claims, apply Step 3 review against the reframes in
references/boundary_canon.md — a lint PASS on non-English text is evidence
of nothing.
Read references/boundary_canon.md (vendored, parity-tracked — see
docs/PARITY.md in the repository) and check, for the classes from Step 1:
| Class | Check |
|---|---|
| A, B | Names used correctly (aegis-trust = SDK; Aegis Core = gateway + crypto core; the package name aegis-sdk is reserved and never used) |
| A, B | Responsibility split — SDK is cooperative hygiene; only Gateway+Core enforce against a non-cooperating agent. Never describe the former as the latter |
| B | LITE/FULL claim separation (inviolable table in the canon) — "Enforced by Aegis Core", "tamper-evident", "policy authorized" are FULL-only vocabulary |
| B | Claim discipline — classify every capability statement as implemented / customer-side / gap+roadmap / never-claim before writing it |
| A, B, C, D | Known pitfalls — references/pitfalls.md |
| D | What may the agent see / do / output: a declared purpose is a label, not authorization; fail-closed beats silent degrade |
Fill templates/boundary_review.md. Decision rules:
The rules above are fixed; everything else adapts. If the situation is not covered, do not guess a rule: return REVIEW, state what could not be checked, and name what the canon would need to cover. If a bundled reference file is missing, that is a STOPPED finding, not a license to improvise.
Provides CDSS development patterns for drug interaction checking, dose validation, clinical scoring (NEWS2, qSOFA), and alert classification integrated into EMR workflows.
npx claudepluginhub incierge3789/aegis-boundary --plugin aegis-boundary