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 agentmods add commands/acaprino/daodan/auditgit clone --depth 1 https://github.com/acaprino/daodanWrote 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/acaprino/daodan/audit)<a href="https://agentmods.dev/commands/acaprino/daodan/audit"><img src="https://agentmods.dev/badge/commands/acaprino/daodan/audit.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 | $0.00072 | $0.01550 |
| Opus 5 | $0.00036 | $0.00775 |
| Sonnet 5 | $0.00014 | $0.00310 |
| Haiku 4.5 | $0.00007 | $0.00155 |
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 3d 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 — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/abstraction-architect:audit
Audit a codebase for structural entropy: duplicated domain knowledge, competing sources of truth, redundant representations, duplicated or derivable state, missed unification, prior art that already exists, and abstractions that are fighting their callers. Report-only.
Usage
/abstraction-architect:audit # audit current directory
/abstraction-architect:audit src/services # audit a subpath
/abstraction-architect:audit --severity-floor high # only high-severity findings
/abstraction-architect:audit --focus knowledge # D1-D4 only
/abstraction-architect:audit --focus D2 # competing sources of truth only
/abstraction-architect:audit --diff # does my change add entropy?
/abstraction-architect:audit --diff origin/master # same, against an explicit base ref
/abstraction-architect:audit --rebuild-index # ignore any existing concept index
Arguments
[path](optional) — codebase root. Default: current working directory.--diff [<base-ref>](optional) — run diff-anchored instead of a whole-codebase audit. Asks the same seven questions as "introduced or aggravated by this change". Base ref defaults to the merge base with the default branch, falling back toHEADfor uncommitted work.--scope <subpath>(optional) — limit findings to a subtree. Deep-dive still runs on the full codebase.--severity-floor low|medium|high(optional) — defaultmedium.--focus all|knowledge|form|D1..D7(optional) — defaultall.knowledgeis D1 to D4,formis D5 to D7, or name a single dimension.--no-index(optional) — do not read or writeconcept-index.json. Use when auditing a directory that is not a git repository, or to measure what the audit finds without a seed.--rebuild-index(optional, global mode only) — ignore any existing index and census the codebase from scratch. Use after a large refactor or a history rewrite.
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.
- 3d ago First seen · 85 lines · 72 tokens per session scan A 5ce9e51833be
audit is a command published in the GitHub repository acaprino/daodan (8 stars, last pushed 8d ago), licensed MIT. It adds 72 tokens to every session and 1,550 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 2026-08-31.
Other commands, from other repositories
git
Git operations with intelligent commit messages and workflow optimization.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.