Borrowing it
Nothing to install: this file belongs to ManSio/mscodebase-intelligence. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/ManSio/mscodebase-intelligence/main/.opencode/command/audit.mdgit clone --depth 1 https://github.com/ManSio/mscodebase-intelligenceWrote 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/commands/mansio/mscodebase-intelligence/audit)<a href="https://agentmods.dev/commands/mansio/mscodebase-intelligence/audit"><img src="https://agentmods.dev/badge/commands/mansio/mscodebase-intelligence/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/commands/mansio/mscodebase-intelligence/audit"><img src="https://agentmods.dev/badge/commands/mansio/mscodebase-intelligence/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 | $0.00010 | $0.00486 |
| Opus 5.5 | $0.00004 | $0.00194 |
| Sonnet 5.5 | $0.00002 | $0.00097 |
| Haiku 4.5 | $0.00001 | $0.00049 |
Grade A, and why
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 26d 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.
What it actually says
You are running the AUDIT phase. The target is not the code — it is the confidence of a number someone might believe.
The trap this exists to prevent
A hand-written list of items makes its own contents eligible by definition. The denominator becomes an assertion dressed as a measurement, and a number built that way can only ever return 100%. Derive the population; never author it.
Order of work
- Derive the population by scanning. A rule that finds candidates, applied to every artifact that carries claims. Print the rule next to the count.
- Separate two different questions.
n_foundis derived by the machine;n_reviewedis authored and starts at 0. Merging them makes coverage 100% by construction. - Triage every finding, by hand. Automated triage was tried twice and both attempts were wrong in opposite directions — a keyword scan missed guarded files, a division regex cited filesystem paths as rate sites. Read the actual line.
- Measure the false-positive share. Until it is measured, the count is not a
verdict.
N findingswithout an FP ratio cannot be published. - Distinguish "wrong" from "dead". A number that no longer reproduces because
the path was deleted by design is
SUPERSEDED, notFALSE. Different action.
After the audit
- Anything that used to be published and no longer reproduces gets a new entry naming the old one. Never silently edit a published number.
- Anything unmeasurable now is
CANNOT VERIFY, notFALSE. - Update the frozen manifest and re-run:
python tools/verification/bootstrap_denominator_manifest.py python tools/verification/g5_denominator.py
Output
## AUDIT — <subject>
**Population:** N derived by <rule>, across <files>
**Triaged:** T true · P partial · F false · U unresolved
**FP share measured:** F/N = <%>
| # | claim | verdict | referent | note |
State plainly which numbers a reader should stop trusting.
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.
- 26d ago First seen · 53 lines · 10 tokens per session scan A 0fd84b28e584
audit is a command published in the GitHub repository ManSio/mscodebase-intelligence (3 stars, last pushed 5d ago), licensed MIT. It adds 10 tokens to every session and 486 once invoked, about $0.0000 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 2026-10-04.
Other commands, from other repositories
index
Index a folder of documents for semantic search.
review-epo-claims
Analyze patent claims for EPO Art. 84 EPC compliance - clarity, conciseness, support by description.
react-native
Command "react-native" from getsentry/toolkit, covering xcode build step (react-native xcode) and important notes.
ingest-dev
Ingest a URL, directory, or file into your knowledge base. remember = a specific durable fact, ingest = a URL, learn = a distilled lesson that gets retrieval preference.
sugar-task
Create a comprehensive Sugar task with rich context and metadata.
resume
Auto-detect and resume any interrupted Plan Cascade task. Detects mega-plan, hybrid-worktree, or hybrid-auto context and routes to the appropriate resume command.