Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add xcrft/mastermind --skill mastermind-audit-attestationgit clone --depth 1 https://github.com/xcrft/mastermindWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/xcrft/mastermind/mastermind-audit-attestation)<a href="https://agentmods.dev/skills/xcrft/mastermind/mastermind-audit-attestation"><img src="https://agentmods.dev/badge/skills/xcrft/mastermind/mastermind-audit-attestation.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00066 | $0.00545 |
| Opus 5 | $0.00033 | $0.00272 |
| Sonnet 5 | $0.00013 | $0.00109 |
| Haiku 4.5 | $0.00007 | $0.00055 |
Grade A, and why
mastermind-audit-attestation scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Mastermind Audit Attestation
Always keep three questions separate: is the content internally intact, who or what authenticated it, and does the verifier's policy accept those claims?
Generate
Create a sealed bundle from an actual spec audit, using an explicit baseline and repository-relative output path:
mastermind audit-spec SPEC --since REF \
--executor-report REPORT --bundle audit-bundle.json
Generation is not verification. Record the resolved repository, full baseline and HEAD OIDs, clean-worktree expectation, and bundle path so verification can use independently trusted values.
Verify
Run with independently trusted expectations:
mastermind audit verify BUNDLE \
--expected-repository OWNER/REPO \
--expected-baseline FULL_OID \
--expected-head FULL_OID \
--root . --json
When a detached signature is required, add both --signature and
--public-key plus --require-signature. Treat a present but invalid signature
as failure; never ignore it.
Explain content_integrity, provenance_authenticity, and
policy_acceptance independently. An unsigned hash is tamper-evident only
relative to trusted expected inputs; it does not prove authorship. A valid key
signature proves control of that key, not identity outside key policy. A GitHub
attestation proves only the issuer/workflow/repository/ref accepted by the
verification policy.
Sign and CI
Sign only when the user explicitly requests it and the private key has safe permissions:
mastermind audit sign BUNDLE --private-key KEY --signature OUT.json
Never display or copy a private key into the repository. For GitHub Actions,
require full commit pins, exact head/repository checks, no secrets or OIDC in
the PR analysis job, and no PR checkout/execution in privileged
workflow_run jobs. Treat downloaded artifacts as hostile until digest,
workflow identity, and envelope policy are verified.
Never call an artifact tamper-proof. Report key rotation, revocation, verifier time, or GitHub-plan limitations when they affect acceptance.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 7d ago First seen · 69 lines · 66 tokens per session scan A 3a7275f39141
mastermind-audit-attestation is a skill published in the GitHub repository xcrft/mastermind (11 stars, last pushed 6d ago), licensed MIT. It adds 66 tokens to every session and 545 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
sem
Use sem to get entity-level (function/class/method) semantic diffs, impact analysis, blame, and dependency context from any Git repo. Trigger this skill whenever the user asks what changed in a commit or PR, wants to understand the blast radius of a change, needs to know who last modified a function, wants to trace…
sem
Semantic version control CLI. Entity-level diffs for Git (functions, classes, methods instead of lines).
truecourse-hooks
Install, configure, or remove the TrueCourse pre-commit hook.
repo-harness-check
Verification entrypoint for repo-harness workflow readiness. Runs workflow gates, task sync, contract checks, inspector, and migration dry-run before merge or release.
repo-harness-ship
Final repo-harness closeout workflow. Runs review/check gates, commits finished contract worktrees, pushes codex branches, and creates GitHub PRs by default.
trace-mcp-pre-commit
Run trace-mcp security, quality-gate, and antipattern checks before committing or opening a PR. Activate when the agent is about to create a commit or pull request in a project indexed by trace-mcp.