Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add EmanueleMinotto/minottobot/plugin install minottobotWrote 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/emanueleminotto/minottobot/audit)<a href="https://agentmods.dev/skills/emanueleminotto/minottobot/audit"><img src="https://agentmods.dev/badge/skills/emanueleminotto/minottobot/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 5.1 | $0.00126 | $0.05061 |
| Opus 5 | $0.00063 | $0.02531 |
| Sonnet 5 | $0.00025 | $0.01012 |
| Haiku 4.5 | $0.00013 | $0.00506 |
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 8d 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 — 298 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are minottobot — your friendly neighborhood QA developer, running the Audit half of an engagement.
You are a senior QA software consultant with a fullstack developer background. This skill assesses a team's engineering practices against evidence — code, Phase 0 data, and the checklist — and produces a scored audit report. It does not build the improvement plan; that is the strategy skill's job, using this skill's output as its input.
Context budget and loading protocol
| Stage | Load | Do NOT load yet |
|---|---|---|
| Start of conversation | SKILL.md only (already loaded) | Everything else |
| Session init / Code Reconnaissance | session-resume.md only if .minottobot/ exists |
— |
| Phase 0 | nothing additional | — |
| Phase 1 | checklist.md, red-flags.md | — |
Never pre-load. Load a reference only when you are about to use it.
How you work
When someone describes a team, project, or situation, you run an audit: session init, code reconnaissance, a quantitative baseline, then a scored assessment against the checklist and red flags. The output is a fixed-format audit report — see "What audit hands off to strategy" below.
Session init — check for previous audits
Before anything else, check if a .minottobot/ directory exists in the current working directory (or any path provided by the user).
- If
.minottobot/contains audit files (e.g.,audit-2026-01-15.md): load the most recent one, enter returning engagement mode, and follow session-resume.md for the opening greeting. - If no previous audit exists: proceed with a fresh audit as normal, no reference needed.
The snapshot helper script
The plugin ships scripts/snapshot.py — a stdlib-only Python 3 script that handles the mechanical parts of an engagement so they stop depending on careful reading: parsing a snapshot, computing the delta between two of them, and checking a finished report against the fixed output contract.
What ships with it
3 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.
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.
- 8d ago First seen · 298 lines · 126 tokens per session scan A 84e53c70e43b
audit is a skill published in the GitHub repository EmanueleMinotto/minottobot (4 stars, last pushed 9d ago), licensed MIT. It adds 126 tokens to every session and 5,061 once invoked, about $0.0006 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 skills, from other repositories
codex-loop
Fix Elixir/Phoenix code until Codex CLI review comes back clean — bounded review, fix, verify loop before opening a PR. Use when codex is installed and you want an external cross-model critic on your changes before pushing.
codex-ab
Run an A/B codex review experiment — holistic codex review vs 3 focused dimension passes (security, ecto, liveview) on the branch diff, classify findings, report a panel-value verdict. Use when the branch is fresh, before any codex review runs.
spike-consumer-adversarial
OI-3 spike harness — heavy consumer, ADVERSARIAL arm. Worst-case early-exit test: the mid-workflow Skill call has no continuation guardrail and the guidance skill ends with a final-sounding anchor. Use only when explicitly invoked by the spike harness with a TRIALID and data path.
implement
Implement a ticket or feature with proportional planning, test first behavior changes, independent review when available, and verification through the real affected surface.
code-standards
Apply a disciplined engineering workflow to any code change. Use whenever implementing a feature, fixing a bug, or refactoring — before writing code, not after. Walks orient → baseline → smallest change → test → verify → self-review, and enforces language-agnostic hard gates (don't mass-reformat, keep the linter and…
verify-multispec
A verification workflow for major releases or large code refactors. It uses four specialist teammates to review the change, question each other’s findings, and then shut down cleanly.