agentmods.dev

manager-audit

manager-audit is a skill for Claude Code from joymin5655/Agent. It costs 138 tokens per session (1,458 once invoked), scanned A, original, MIT.

A read-only checker for a supervised coding run. It reviews the run's logs across four areas: understanding the request, model routing, token use, and following the required process.

In plain words
What is it for?
Auditing supervise runs, ranking sources of token waste, checking model choices and required review steps, and writing proposed fixes to PROPOSALS.md for approval.
Why use it?
It shows whether the supervisor followed its own rules and identifies waste or missing steps without changing the run.

Skill for Claude Code

Written for Claude Code: when-to-use in frontmatter.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the agent-harness-extras plugin — 10 skills, 1 agent shipped together

not rated 2repo changed 6d ago A scan 138 tokens original MIT

Good fit Auditing supervise runs, ranking sources of token waste, checking model choices and required review steps, and writing proposed fixes to PROPOSALS.md for approval.

Compare 6 skills from other repositories ↓
View source ↗ joymin5655/Agent
Install

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.

Claude Code
/plugin marketplace add joymin5655/Agent
Claude Code
/plugin install agent-harness-extras

Made for: Claude Code.

Or install agent-harness-extras, the plugin that ships this one along with the rest of its 10 skills, 1 agent.

Wrote 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.

agentmods badge for manager-audit

README.md
[![agentmods](https://agentmods.dev/badge/skills/joymin5655/agent/manager-audit/github.svg)](https://agentmods.dev/skills/joymin5655/agent/manager-audit)
Your own site
<a href="https://agentmods.dev/skills/joymin5655/agent/manager-audit"><img src="https://agentmods.dev/badge/skills/joymin5655/agent/manager-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.

agentmods 80×15 button for manager-audit

Your own site · 80×15
<a href="https://agentmods.dev/skills/joymin5655/agent/manager-audit"><img src="https://agentmods.dev/badge/skills/joymin5655/agent/manager-audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 138 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,458 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00138 $0.01458
Opus 5.5 $0.00055 $0.00583
Sonnet 5.5 $0.00028 $0.00292
Haiku 4.5 $0.00014 $0.00146

Measured 6d ago against content hash 0418069c17ee, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

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 6d 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.

extras/skills/manager-audit/SKILL.md · 121 lines

How it starts

The opening of the file, as written. The whole thing — 121 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 (a fifth lane covers review completeness and runs only in the slug-less --global sweep):

  1. 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.
  2. 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 from docs/model-routing.md, measured by core/hooks/model-routing-observer.py).
  3. 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.
  4. 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.

A fifth lane runs only with --global (no slug): review-completeness — how often a review was Claude-only (V-6). It reads $HR/core/infra/telemetry-digest.sh --review --window 30 --json: WARN solo-ratio-high when the share of reviewed diffs with no external-vendor complete review exceeds AGENT_REVIEW_SOLO_MAX percent (default 50), WARN override-used when any review override was logged (count only, the reason is never shown), INFO review-unmeasured when no row names its author (no data, or only rows from before author_vendor was recorded) — unmeasured is never reported as clean.

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

HR="$(bash "${CLAUDE_PLUGIN_ROOT}/scripts/harness-root.sh")"   # core plugin root (extras ships skills only)
[ -n "$HR" ] && bash "$HR/core/infra/manager-audit.sh" <slug> --json   # empty HR = core not found: stop and tell the user

Read the full file on GitHub · 121 lines

Changes

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.

  1. 6d ago Changed · +1 lines 0418069c17ee
  2. 14d ago Changed b12aeb5fa57f
  3. 16d ago Changed · +1 lines · +138 tokens per session 26238a9e9c81
  4. 29d ago Changed · +10 lines · -125 tokens per session 99bd9a41b192
  5. 1mo ago Changed · +1 lines b8792e6c59d7
  6. 2mo ago First seen · 108 lines · 125 tokens per session scan A eb2a9acc9d26

Subscribe to this mod's changes

manager-audit is a skill published in the GitHub repository joymin5655/Agent (2 stars, last pushed yesterday), licensed MIT. It adds 138 tokens to every session and 1,458 once invoked, about $0.0006 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 2026-08-31.

Analytics and metricsBuilding agentsClaude CodeLLMagent-infrastructureai-agentsdevtoolspolicy-as-code
Related

manager-audit compared with skills from other repositories

manager-audit next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
manager-auditjoymin5655/AgentSkill2yesterdayMITA138Claude Code
agent-prompt-auditavibe-bot/avibeSkill637yesterdayMITA105Codex
computer-useavibe-bot/avibeSkill637yesterdayMITA19Claude Code, Codex
background-watch-hookavibe-bot/avibeSkill637yesterdayMITA32Claude Code, Codex
use-avibe-harnessavibe-bot/avibeSkill637yesterdayMITA36Claude Code, Codex
use-avibe-vaultavibe-bot/avibeSkill637yesterdayMITA36Claude Code, Codex
use-show-pagesavibe-bot/avibeSkill637yesterdayMITA39Claude Code, Codex