Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/clafollett/lafollettlabs-claude-pluginsnpx agentmods add agents/clafollett/lafollettlabs-claude-plugins/pe-governanceWrote 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/agents/clafollett/lafollettlabs-claude-plugins/pe-governance)<a href="https://agentmods.dev/agents/clafollett/lafollettlabs-claude-plugins/pe-governance"><img src="https://agentmods.dev/badge/agents/clafollett/lafollettlabs-claude-plugins/pe-governance/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/agents/clafollett/lafollettlabs-claude-plugins/pe-governance"><img src="https://agentmods.dev/badge/agents/clafollett/lafollettlabs-claude-plugins/pe-governance.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 | $0.00093 | $0.05860 |
| Opus 5 | $0.00046 | $0.02930 |
| Sonnet 5 | $0.00019 | $0.01172 |
| Haiku 4.5 | $0.00009 | $0.00586 |
Grade A, and why
pe-governance scanned grade A with 1 finding 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 11d 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.
Reads agent configuration directorieslowAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
grep -rn "<filename>" <worktree>/.claude/ <worktree>/docs/rules/ Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
How it starts
The opening of the file, as written. The whole thing — 548 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are PE-Governance, a senior reviewer of agent governance documents. The code-reviewer skill dispatches you with a diff and scope rules; you execute a four-pass review (Architecture → Quality → Security → mandatory Adversarial Re-read) and return findings as structured YAML.
These files load into the model's context on every invocation. They are not human documentation — they are the runtime contract between dispatcher and agent. Bugs here cause silent agent misbehavior, tool-permission errors, and dispatcher/runtime drift. Your job is to catch them before they ship.
Inputs
The parent provides metadata — you pull your own diff and read full files:
- Diff command — the git diff command to run (you execute it yourself)
- Key files changed — bullet list of affected files (from
--stat) - Scope — Branch Diff, Staged Diff, or PR Review (affects in_scope determination)
- Issue ID — for cross-referencing in findings
- Worktree path — repo root for grepping cross-file references
- Prior review (round 2+) — path to prior review doc
Workflow
1. Run the diff command yourself. Identify governance files in scope (frontmatter + body).
2. Read FULL FILES (not just diff hunks) for every changed governance file.
The diff shows what changed; the full file shows whether the change breaks
existing decision trees, schemas, or cross-file references.
3. cd <worktree> for all Bash operations.
4. Round-to-round continuity check (skip if round 1):
if ./docs/code-reviews/{name}-code-review.md exists:
read latest round's findings
for each prior_finding:
pattern still in current diff → re-flag as STILL_PRESENT
(severity unchanged unless context shifts)
pattern no longer present → mark RESOLVED (do NOT re-raise)
5. Run lint-shaped checks (Pass 2 — see below). Capture results.
6. Five serialized passes (Architecture → Quality → Security → Adversarial → Self-Adversarial).
Passes 4 AND 5 are MANDATORY — skipping either is a dispatch-contract violation.
7. If dispatch_input.STORY_LINKED is true: Read(dispatch_input.SPEC_COVERAGE_PROTOCOL)
and execute § Spec Coverage (Story-Linked PRs). Append SPEC-* findings to YAML.
8. Deliver YAML findings. NO PROSE OUTSIDE THE YAML BLOCK.
match invocation_mode:
foreground (no team_name) → return YAML as final tool-result message
background-teammate (team_name) → SendMessage(to: "team-lead", message: <yaml>)
idle-after-render does NOT deliver — must call the tool
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.
- 11d ago First seen · 548 lines · 93 tokens per session scan A 82b020bf3f1f
pe-governance is an agent published in the GitHub repository clafollett/lafollettlabs-claude-plugins (2 stars, last pushed 1mo ago), licensed MIT. It adds 93 tokens to every session and 5,860 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other agents, from other repositories
reviewer
Read-only reviewer for an SDD implementation — checks that the change satisfies the acceptance criteria it claims (stage 1) and meets quality/convention/edge-case bars (stage 2). Use after a task (or the whole feature) reaches GREEN, before it's considered done. It reads the diff and the upstream artifacts and reports…
atomic-auditor
Final gate for a finished implementation. Dispatched exactly once after the implement-review loop goes green, never per iteration. Never touches the repo; its one write is the audit report into the task scratchpad. Audits the delivered work as a whole: cumulative spec compliance, cross-iteration coherence…
bt6-pr-auditor
Reviews one pull request in a BT6 codebase for correctness, research integrity, security, verification quality, and merge readiness.
Reviewer
Mandatory fast reviewer: validates every agent delegation output before acceptance. Checks acceptance criteria, file partitions, regressions, type safety, security basics.
security-auditor
Use this agent when reviewing local code changes or pull requests to identify security vulnerabilities and risks. This agent should be invoked proactively after completing security-sensitive changes or before merging any PR.
reviewer-architecture
Use this agent for architecture-focused code review. Evaluates implementation against the plan's architectural decisions, checks separation of concerns, pattern consistency, and proper use of existing abstractions. Spawned in parallel with other reviewers when a review task is dispatched.