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 Ashkaan/contextium --skill spec-auditgit clone --depth 1 https://github.com/Ashkaan/contextiumWrote 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/ashkaan/contextium/spec-audit)<a href="https://agentmods.dev/skills/ashkaan/contextium/spec-audit"><img src="https://agentmods.dev/badge/skills/ashkaan/contextium/spec-audit/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/ashkaan/contextium/spec-audit"><img src="https://agentmods.dev/badge/skills/ashkaan/contextium/spec-audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 3 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Agent Snooping · line 11 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
- medium Agent Snooping · line 17 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
- medium Agent Snooping · line 18 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
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 | $0.00208 | $0.04455 |
| Opus 5.5 | $0.00083 | $0.01782 |
| Sonnet 5.5 | $0.00042 | $0.00891 |
| Haiku 4.5 | $0.00021 | $0.00445 |
Grade A, and why
spec-audit 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 11d 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 — 184 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/spec-audit — adversarial SPEC pre-review
Run reviewer consensus (correctness) + spirit-check (fidelity to user's ask) on a freshly-written or materially-rewritten SPEC, BEFORE presenting it to the user for sign-off.
Invoked by /spec immediately after it writes the SPEC (UNCONDITIONAL — every SPEC goes through this review), by /implement when revising a SPEC mid-flight, or by any subagent that writes a SPEC. The verdict is a record, not a gate: the single consolidated spec-audit: line is written into the spec's plan.md Constitution Check by scripts/write-audit-line.ts, and the close's journal entry quotes it.
Works on any SPEC shape. The common one is a project spec folder, projects/<domain>/<date>_<slug>/specs/NNN-name/, holding spec.md, plan.md, tasks.md and research.md from .agents/skills/spec/references/templates/. Pass the FOLDER: every script here accepts one wherever it accepts a file — check-materiality.ts diffs the whole folder, and spec-audit.ts hands the reviewer all four files, each under a === <file> === header. A single file still works for the single-file shapes: app SPECs (apps/<name>/SPEC.md) and feature SPECs (apps/<name>/specs/YYYY-MM-DD_<feature>.md) when an existing one is materially rewritten. Spirit-check's required input is always present: in a folder it is spec.md's **Input**, ## Clarifications, ## User Scenarios & Testing and ## Requirements plus plan.md's ### Simplest shape; in a single-file SPEC it is § 0, § 0a, § 0b and § 1. This skill audits whatever it is handed and does not choose the location.
Critical
- No silent revision. Whatever the user signs off on at step 6 MUST be byte-identical to what gets committed. Zero edits between user sign-off and
git commit. deferis forbidden as an annotation on reviewer findings. If you want to defer a finding, ask the user instead (a numbered list, recommendation first; in Claude Code,AskUserQuestion).- Materiality is a script result, not a judgment. Run
scripts/check-materiality.tsto decide; don't infer from prose.
What ships with it
8 files 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.
- scripts/check-materiality.test.ts 16 KB runs code
- scripts/check-materiality.ts 15 KB runs code
- scripts/format-trailer.test.ts 8.8 KB runs code
- scripts/format-trailer.ts 5.8 KB runs code
- scripts/parse-review-output.test.ts 9.3 KB runs code
- scripts/parse-review-output.ts 4.7 KB runs code
- scripts/write-audit-line.test.ts 4.9 KB runs code
- scripts/write-audit-line.ts 3.4 KB runs code
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.
- 11d ago Changed · -17 tokens per session b03e55ea0116
- 25d ago Changed · +3 lines cd04ed4828fa
- 26d ago Changed · +113 tokens per session d375625b0bad
- 27d ago Changed · -55 lines · +35 tokens per session c43b0013eb83
- 1mo ago Changed 2a2ad0b55acf
- 1mo ago First seen · 236 lines · 77 tokens per session scan A 2b0040aa6fbc
spec-audit is a skill published in the GitHub repository Ashkaan/contextium (36 stars, last pushed 12d ago), licensed MIT. It adds 208 tokens to every session and 4,455 once invoked, about $0.0008 per session on Opus 5.5. 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
red-team-review
Unified adversarial review, two modes. Strategic Matrix v4.3 (MTA-004) for arguments/plans/decisions: Priors → Rubric → Adversarial Lenses → SWOT/TOWS → MCDA → Blind Spot/Kill Switch → Summary. Deliverable Audit for built artefacts (assignments, reports, code outputs): isolated fresh-context hunt against the brief…
decision-journal
Unified decision lifecycle: Pre-decision logging, post-decision review, failure classification, and calibration tracking. Absorbs: post-mortem-engine.
plan-review-architecture
Architecture-dimension reviewer for written plans. Use when running plan-review or directly when an architectural review is wanted. Activate for keywords like "architecture review", "data flow", "failure modes", "rollback", "edge cases", "test matrix". Scores 5 sub-dimensions 0-10, produces ranked fixes. Always cite…
code-review-loop
Use when opening a PR for review or when receiving review feedback. Activate for keywords like "code review", "PR review", "request review", "review feedback", "address comments", "reviewer said". Covers both ends of the loop: preparing a reviewable PR and acting on feedback rigorously. Always engage with every…
example-skill
Performs thorough code reviews following best practices. Use when reviewing pull requests, checking code quality, or ensuring coding standards compliance.
code-review
Analyze diffs, suggest improvements, and review pull requests with actionable feedback.