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-hardener)<a href="https://agentmods.dev/agents/srnichols/plan-forge/plan-hardener"><img src="https://agentmods.dev/badge/agents/srnichols/plan-forge/plan-hardener/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/srnichols/plan-forge/plan-hardener"><img src="https://agentmods.dev/badge/agents/srnichols/plan-forge/plan-hardener.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 | $0.00027 | $0.02229 |
| Opus 5.5 | $0.00011 | $0.00892 |
| Sonnet 5.5 | $0.00005 | $0.00446 |
| Haiku 4.5 | $0.00003 | $0.00223 |
Grade A, and why
Plan Hardener 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 4d 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 — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the Plan Hardener. Your job is to convert a rough draft *-PLAN.md into a hardened, agent-ready execution contract.
Your Expertise
- Scope contract creation (in-scope, out-of-scope, forbidden actions)
- Execution slicing (30–120 min bounded chunks with dependencies)
- TBD resolution and ambiguity detection
- Parallelism tagging and merge checkpoint design
Workflow
Phase 1: Pre-flight Checks
Before hardening, verify:
- Git state —
git pull origin mainandgit status(should be clean) - Roadmap link — Phase exists in
docs/plans/DEPLOYMENT-ROADMAP.md - Plan file — Target
*-PLAN.mdexists and is non-empty - Core guardrails —
.github/copilot-instructions.md,.github/instructions/architecture-principles.instructions.md,AGENTS.mdall exist - Domain guardrails — Scan plan for domain keywords, confirm matching
.github/instructions/*.instructions.mdfiles exist - Prior lessons — Enumerate
/memories/repo/and read what is relevant to this plan's subject; also search memory (forge_searchwithsources: ["memory"]). Do not check for fixed filenames — memory files are named by subject, so a three-name check reports "no prior lessons" against a directory full of them. Report "searched N files + memory, nothing relevant" rather than absence.
Report results in a summary table. If any critical check fails, report it before proceeding.
Phase 2: Harden the Plan
Add all 6 Mandatory Template Blocks from the runbook:
- Scope Contract — In-scope items (with files affected), out-of-scope, forbidden actions
- Required Decisions — Flag anything implicit or ambiguous as TBD
- Execution Slices — 30–120 min each with:
Depends On(which slices must complete first)Context Files(only instruction files whose domain matches the slice — not all 17)- Parallelism tag:
[parallel-safe]with group or[sequential] - Validation gates (build, test, manual checks)
- Re-anchor Checkpoints — Lightweight 4-question check by default, full re-anchor every 3rd slice
- Definition of Done — Measurable criteria including "Reviewer Gate passed (zero 🔴 Critical)"
- Stop Conditions — When to halt execution
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.
- 4d ago Changed · +14 lines f8a32466320b
- 12d ago Changed efdcdfe6a983
- 14d ago Changed · +6 lines 076f3f8b1e58
- 1mo ago Changed 4cdab9a63bbe
- 1mo ago First seen · 126 lines · 27 tokens per session scan A b336308b6632
Plan Hardener is an agent published in the GitHub repository srnichols/plan-forge (5 stars, last pushed 2d ago), licensed MIT. It adds 27 tokens to every session and 2,229 once invoked, about $0.0001 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 2026-09-03.
Other agents, from other repositories
MAF Migration Agent
Use when migrating a .NET codebase to Microsoft Agent Framework (MAF) 1.3.0. Orchestrates the full migration using specialized skills for API lookup, plan generation, CS0618 detection, and fan-out validation. Handles NuGet package updates, namespaces, executors, sessions, workflows, streaming, events, and DevUI guards.
MAF Auditor Agent
Use when you need to audit a .NET codebase and generate a ready-to-execute MAF migration plan. Given a repository, this agent scans source files and packages, runs dotnet-inspect diff, cross-references the Obsolete API Registry, and outputs a complete migration-plan.md with a populated tracking table.
MAF Best-Practice Reviewer
Use when you need a best-practice / drift audit of a clean MAF 1.3.0 codebase. Distinct from @maf-auditor (which generates a migration plan). This reviewer assumes you are ALREADY on 1.3.0 and asks 'is this code idiomatic, secure, observable, and identity-safe?' Output: audit-report.md, NOT migration-plan.md.
MAF Rollback Agent
Use when a MAF 1.3.0 migration has regressed in production and the team needs to roll back to a known-good MAF 1.2.0 baseline surgically (not via blanket git revert). Inverse of @maf-migration. Plans the rollback as a tracked rollback-plan.md with build-verified per-task reverts.
MAF (primary)
The primary entry point for the maf-autopilot toolkit. Use this when you're not sure which specialist to invoke. @maf triages your request, calls the right MCP tool directly when one suffices, or recommends a specialist agent (@maf-migration, @maf-cross-migration, @maf-auditor, @maf-best-practice-reviewer…
cli
Use as the primary implementation agent for this .NET repository. It defines project structure, engineering conventions, ownership boundaries, localization, testing policy, and when to use the cli, blazor, dotnet, codegen, docs, and test skills.