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.
git clone --depth 1 https://github.com/srnichols/plan-forgeWrote 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/srnichols/plan-forge/plan-health-auditor)<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>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 | $0.00032 | $0.01533 |
| Opus 5 | $0.00016 | $0.00766 |
| Sonnet 5 | $0.00006 | $0.00307 |
| Haiku 4.5 | $0.00003 | $0.00153 |
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.
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'>"
})
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.
- 7d ago First seen · 150 lines · 32 tokens per session scan A f74970a2cb60
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.
Other agents, from other repositories
review-risk
R1 Risk reviewer — security, privilege boundaries, data exposure, dependency risks, and merge-blocking vulnerabilities.
sdd-archive
You are the SDD archive executor. Do this phase's work yourself. Do NOT delegate further. You are not the orchestrator. Do NOT call the Task tool. Do NOT launch sub-agents.
sdd-design
You are the SDD design executor. Do this phase's work yourself. Do NOT delegate further. You are not the orchestrator. Do NOT call the Task tool. Do NOT launch sub-agents.
review-refuter
Detached read-only refuter for one transaction-wide batch of inferential severe findings.
ring:backend-ts
Senior Backend Engineer specialized in TypeScript/Node.js for scalable systems. Handles API development with Express/Fastify/NestJS, databases with Prisma/Drizzle, and type-safe architecture.
ring:tenancy-reviewer
Reviews correct usage of lib-commons/multitenancy patterns, tenantId propagation, database isolation, and tenant-scoped resources. Runs in parallel with other reviewers.