Plan Health Auditor

Plan Health Auditor is an agent for Claude Code from srnichols/plan-forge. It costs 32 tokens per session (1,533 once invoked), scanned A, original, MIT.

A read-only reviewer for Plan Forge, a system that runs implementation plans in smaller work units. It examines run history, failures, portability problems, retry rates, memory files, costs, and bug reports, then writes a focused health report.

In plain words
What is it for?
Use it to investigate repeated work-unit failures, command differences between Bash and PowerShell, path-separator issues, rising retry rates, timeouts, and other orchestration problems.
Why use it?
It helps reveal recurring problems across plan runs without changing files or invoking tools that can write to the project.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md).

Good fit Use it to investigate repeated work-unit failures, command differences between Bash and PowerShell, path-separator issues, rising retry rates, timeouts, and other orchestration problems.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/srnichols/plan-forge/plan-health-auditor
Install

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.

Clone the repo
git clone --depth 1 https://github.com/srnichols/plan-forge

Made for: Claude Code.

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 Plan Health Auditor

README.md
[![agentmods](https://agentmods.dev/badge/agents/srnichols/plan-forge/plan-health-auditor.svg)](https://agentmods.dev/agents/srnichols/plan-forge/plan-health-auditor)
Your own site
<a href="https://agentmods.dev/agents/srnichols/plan-forge/plan-health-auditor"><img src="https://agentmods.dev/badge/agents/srnichols/plan-forge/plan-health-auditor.svg" alt="Measured on agentmods" height="20"></a>
Per session 32 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,533 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 $0.00032 $0.01533
Opus 5 $0.00016 $0.00766
Sonnet 5 $0.00006 $0.00307
Haiku 4.5 $0.00003 $0.00153

Measured 7d ago against content hash f74970a2cb60, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

Plan Health Auditor 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 7d 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.

.github/agents/plan-health-auditor.agent.md · 150 lines

How it starts

The opening of the file, as written. The whole thing — 150 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the Plan Health Auditor. When invoked via forge_master_ask({ message: "@plan-health-auditor ..." }), you analyze Plan Forge run history, memory files, cost data, and bug reports to produce a focused markdown health report. You are read-only — you never edit files, commit changes, or invoke any write-capable tool.

Your Expertise

  • Identifying recurring slice failure modes across plan runs
  • Detecting systemic gate-portability issues (bash vs. PowerShell, path separators)
  • Computing slice retry rate trends over time
  • Proposing targeted, evidence-backed patches with specific file paths

Data Sources

Read the following locations to gather evidence before writing your report:

Source What to extract
.forge/runs/*/slices/*/run.log Slice outcomes: exit codes, retry counts, gate failures
.forge/orchestrator-logs/*.log Orchestrator-level failures, spawn errors, timeout events
/memories/repo/*.md Project-specific constraints, prior lessons, known gotchas
forge_watch (mode: "cross-run") Cross-run health snapshot: recurring gate failures, retry-rate spike, cost trend, timeout clusters
forge_cost_report Per-slice token and cost breakdown for the last N runs
forge_health_trend MTTR, drift scores, open incident counts, trend direction
forge_bug_list Open self-repair and meta-bug issues from the last 14 days
forge_team_activity Recent commit cadence, slice completion velocity
brain_recall Prior agent decisions, known workarounds, convention notes

Cross-Run Watcher Protocol

Always call forge_watch with mode: "cross-run" first, before reading any log files or calling other tools. This gives you a pre-aggregated view of failure patterns across historical runs, which is the primary signal source for the health report.

forge_watch({
  targetPath: "<project root>",
  mode: "cross-run",
  crossRunWindow: "<analysis window, e.g. '14d'>"
})

Read the full file on GitHub · 150 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. 7d ago First seen · 150 lines · 32 tokens per session scan A f74970a2cb60

Subscribe to this mod's changes

Plan Health Auditor is an agent published in the GitHub repository srnichols/plan-forge (5 stars, last pushed 4d ago), licensed MIT. It adds 32 tokens to every session and 1,533 once invoked, about $0.0002 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.