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 srmackey/insitu --skill protocol-auditgit clone --depth 1 https://github.com/srmackey/insituWrote 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/srmackey/insitu/protocol-audit)<a href="https://agentmods.dev/skills/srmackey/insitu/protocol-audit"><img src="https://agentmods.dev/badge/skills/srmackey/insitu/protocol-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/srmackey/insitu/protocol-audit"><img src="https://agentmods.dev/badge/skills/srmackey/insitu/protocol-audit.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00089 | $0.03041 |
| Opus 5 | $0.00044 | $0.01520 |
| Sonnet 5 | $0.00018 | $0.00608 |
| Haiku 4.5 | $0.00009 | $0.00304 |
Grade A, and why
protocol-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 today.
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 — 150 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Protocol audit
Read what a chair actually loads and judge whether it still holds together. Output is a proposal. This skill never edits a protocol, a map, an article, or a pack.
The job is reading comprehension, not computation. No tool finds these problems for you. The tools hand you the text and the facts; the finding is yours.
Scope
| Ask | You do |
|---|---|
| No argument, or "this chair" | Audit the working folder you are in. |
| A project key that is not this folder | Read it freely. Holding the report is admin only, so confirm the class with operators. If this chair is bound, the finding leaves as an export instead of becoming a report here. |
sweep plus keys |
Admin only, and only on a charter the principal named. One report per chair, then the roll-up in §7. |
The cross-chair rule is about ownership, not permission. Inspect is free to every class, so nothing stops a bound chair from reading another project's composition, and you may well end up doing that to check whether a finding is local or systemic. What a bound chair must not do is hold a report about a chair it cannot act on. Findings about another chair are not closable where you are sitting, and parking them in this chair's records is the mistake methodology/status-contract exists to prevent. If you are bound and you find something about a sibling, it leaves as an export under methodology/envoy-mail. It does not become your open loop.
A sweep is not a license to roam. If the principal did not name which maps are in scope, ask before reading them.
1. Load the picture
Before judging anything, get the whole composed text in front of you, plus the facts about where it came from.
project_statusfor the map, the roles, the imports, the sizes, and whether the disk copy matches.resolve_protocolfor the composed text. Read it. All of it. An audit of a summary is worthless.list_articlesfor the catalog with origins, so you know which members are native to the vault and which arrived in a pack.where_usedon anything you suspect, because a finding that touches one map is local and one that touches five is a pack problem.- The chair's own constitution and native files. The protocol is only half of what the agent loads, and half the contradictions are between the two.
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.
- today First seen · 150 lines · 89 tokens per session scan A 6f8027b9a4e2
protocol-audit is a skill published in the GitHub repository srmackey/insitu (0 stars, last pushed today), licensed MIT. It adds 89 tokens to every session and 3,041 once invoked, about $0.0004 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 2026-09-17.
Other skills, from other repositories
code-review
Reviews a supplied code path or diff for correctness, security, maintainability, and style without executing or modifying it.
knowledge-audit
Review and clean up stored memories — find duplicates, contradictions, stale entries, and consolidate.
review-guidelines
Additional code review guidelines specific to this codebase. Auto-loaded by the review agent during PR reviews to enforce project conventions.
tool-defs-analysis
Read-only audit of MCP definition language across an existing surface — tools, resources, prompts, server instructions. Walks every definition file and checks 16 categories the LLM reads to decide whether and how to call: voice & tense, internal leaks, audience leaks, defaults, recovery hints, field descriptions…
research-papers
Use when the user wants a literature review, paper summary, research landscape, or sourced synthesis from papers, reports, abstracts, or converted PDFs.
gitnexus-pr-review
Use when the user wants to review a pull request, understand what a PR changes, assess risk of merging, or check for missing test coverage. Examples: "Review this PR", "What does PR #42 change?", "Is this PR safe to merge?".