Borrowing it
Nothing to install: this file belongs to srnichols/plan-forge. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/srnichols/plan-forge/master/.github/instructions/ai-plan-hardening-runbook.instructions.mdgit 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/instructions/srnichols/plan-forge/ai-plan-hardening-runbook)<a href="https://agentmods.dev/instructions/srnichols/plan-forge/ai-plan-hardening-runbook"><img src="https://agentmods.dev/badge/instructions/srnichols/plan-forge/ai-plan-hardening-runbook/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/instructions/srnichols/plan-forge/ai-plan-hardening-runbook"><img src="https://agentmods.dev/badge/instructions/srnichols/plan-forge/ai-plan-hardening-runbook.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 | $0.00503 | $0.00503 |
| Opus 5 | $0.00251 | $0.00251 |
| Sonnet 5 | $0.00101 | $0.00101 |
| Haiku 4.5 | $0.00050 | $0.00050 |
Grade A, and why
plan-forge ai-plan-hardening-runbook.instructions.md 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 9d 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.
What it actually says
Plan Forge — Quick Reference
Full Runbook: AI-Plan-Hardening-Runbook.md Step-by-Step: AI-Plan-Hardening-Runbook-Instructions.md
Pipeline Summary
SESSION 1 → Harden (scope contract, execution slices, validation gates)
SESSION 2 → Execute (slice-by-slice, commit after each) + Completeness Sweep
SESSION 3 → Review & Audit (fresh agent, read-only, drift detection)
Key Concepts
- 3 separate sessions: Harden, Execute, Review (prevents context bleed)
- 6 Mandatory Blocks: Scope Contract, Required Decisions, Execution Slices, Re-anchor, Definition of Done, Post-Mortem
- Validation after every slice: Build + test must pass before moving on
- Re-anchor after every slice: Re-read Scope Contract to prevent drift
- Stop on ambiguity: Never guess — ask
When Editing Plan Files
- Every
*-PLAN.mdmust contain all 6 Mandatory Template Blocks - Execution slices should be 30-120 minutes each
- Each slice needs at least one concrete validation gate
- Tag slices
[parallel-safe]or[sequential] - Include
Context Filesper slice (especially.github/instructions/*.instructions.md) - Never nest escaped double-quotes inside
bash -c "..."(meta-bug #93). On Windowscmd → bash, three-level escapes likebash -c "grep -q onclick=\\\"foo\\\" file"collapse with/bin/bash: -c: line 1: unexpected EOF while looking for matching quote. Use single quotes inside ('foo'), switch to anode -eone-liner using.includes(), or rely on a vitest test that already proves the presence/absence. The full Gate Portability Rules live instep2-harden-plan.prompt.md.
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.
- 9d ago First seen · 40 lines · 503 tokens per session scan A 25b78001c3da
plan-forge ai-plan-hardening-runbook.instructions.md is an instructions file published in the GitHub repository srnichols/plan-forge (5 stars, last pushed yesterday), licensed MIT. It adds 503 tokens to every session, about $0.0025 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 instructions, from other repositories
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.