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 skills/joymin5655/agent/manager-auditnpx skills add joymin5655/Agent --skill manager-auditgit clone --depth 1 https://github.com/joymin5655/AgentWrote 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/joymin5655/agent/manager-audit)<a href="https://agentmods.dev/skills/joymin5655/agent/manager-audit"><img src="https://agentmods.dev/badge/skills/joymin5655/agent/manager-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 | $0.00125 | $0.01192 |
| Opus 5 | $0.00063 | $0.00596 |
| Sonnet 5 | $0.00025 | $0.00238 |
| Haiku 4.5 | $0.00013 | $0.00119 |
Grade A, and why
manager-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 — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/manager-audit
Goal
One interpreted verdict over a supervise run, answering four questions the supervisor cannot be trusted to answer about itself:
- Did it restate the ask? — lane
restatement-quality: the intake restatement exists, all six sections are filled, success criteria are measurable, no wave drifts outside the interpreted goal. - Did it route models per policy? — lane
routing-waste: no silent TOP-inherit leaks, verify/judge never below the MID floor, fan-out at LOW (conventions fromdocs/model-routing.md, measured bycore/hooks/model-routing-observer.py). - Where did the tokens go? — lane
token-spend: relative dispatch cost (tokens × tier multiplier — relative ranges from docs/model-routing.md, never prices), top waste sources ranked. - Did it follow its own loop? — lane
role-compliance: every wave audited, never-auto-retry honored, RECORD.md written, review lane dispatched after code waves.
The machine layer detects; this skill interprets and proposes. The split mirrors harness-audit: deleting this skill weakens no gate.
Steps
1. Run the machine layer
bash core/infra/manager-audit.sh <slug> --json
Optional: --session <id> to scope routing records to one session. Render the
findings as a per-lane table (lane / check / severity / evidence). The script
always exits 0 — severity lives in the findings, not the exit code.
2. Interpret the semantic halves
The script flags candidates it cannot judge; judge them here (this is judgment work — it stays in the main loop, no dispatch):
scope-drift-candidate— read the flagged wave and the restatement's Interpreted goal. A wave phrased differently but serving the goal is a false positive: mark itdismissedwith one line of reasoning. A wave serving an unstated goal is real drift: keep it.top-inherit-leak— an unpinned dispatch is legitimate for judgment work (planning, synthesis — the Model policy's inherit lane). Check what the dispatched agent actually did; keep only leaks on execution/lookup/ fan-out work.top-tier-dominates— expected when the run was genuinely judgment-heavy; keep only if execution waves ran inline or at TOP.
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 · 108 lines · 125 tokens per session scan A eb2a9acc9d26
manager-audit is a skill published in the GitHub repository joymin5655/Agent (2 stars, last pushed 9d ago), licensed MIT. It adds 125 tokens to every session and 1,192 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
regex-mastery
Use this skill when writing regular expressions, debugging pattern matching,optimizing regex performance, or implementing text validation. Triggers on regex, regular expressions, pattern matching, lookahead, lookbehind, named groups, capture groups, backreferences, and any task requiring text pattern matching.
background-watch-hook
Use vibe watch to run a managed Harness waiter that returns to the same conversation later. Best for reviews, CI, files, logs, and other wait-now-continue-later workflows.
pr-delivery-loop
The implementation-lane standard for delivering a PR across the Avibe repositories (avibe, avibe-backend, avibe-docs, avault, and vault-sandbox) — branch/scope rules, contracts, Codex-bot review-loop discipline, and close-out criteria. Use this skill for every implementation task in these repos, regardless of agent…
technocore-chat
Coordinate with other AI agents over plain HTTP GETs — shared rooms, durable notes, long-polling. No POST, no sockets, no client libraries, no account; a fetch tool is enough, and an MCP server fronts the same surface. Use when you need to leave a message for another agent, wait for one, or persist state across your…
goal-flight
Portable Goal Flight workflow for long-running repo work: planning, dispatch, review, recovery, file-backed resume.
shell-scripting
Use this skill when writing bash or zsh scripts, parsing arguments, handling errors, or automating CLI workflows. Triggers on bash scripting, shell scripts, argument parsing, process substitution, here documents, signal trapping, exit codes, and any task requiring portable shell script development.