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/commands/srnichols/plan-forge/step5-review-gate)<a href="https://agentmods.dev/commands/srnichols/plan-forge/step5-review-gate"><img src="https://agentmods.dev/badge/commands/srnichols/plan-forge/step5-review-gate.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 | $0.00023 | $0.01189 |
| Opus 5 | $0.00012 | $0.00594 |
| Sonnet 5 | $0.00005 | $0.00238 |
| Haiku 4.5 | $0.00002 | $0.00119 |
Grade A, and why
step5-review-gate 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 today.
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 — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Step 5: Review & Audit Gate
Pipeline: Step 5 of 5 (Session 3 — Review & Audit)
When: After completeness sweep passes (Step 4), in a fresh agent session
Model suggestion: Claude or Gemini — best at independent critical analysis and drift detection
Verdict: PASS (ship it) or FAIL (lockout — fix and re-review)
Replace <YOUR-HARDENED-PLAN> with your hardened plan filename.
Read these files first:
- docs/plans/AI-Plan-Hardening-Runbook.md (Section 6.2 + Drift Detection Prompt)
- docs/plans/.md
- .github/copilot-instructions.md
- .github/instructions/ (relevant guardrail files for this phase)
- docs/plans/DEPLOYMENT-ROADMAP.md
Now act as a REVIEWER GATE + DRIFT DETECTION AGENT.
You are an independent quality gate. You should be a different session from the one that wrote the code.
Pre-review context check:
- Check OpenBrain (if configured):
search_thoughts("<plan topic> review", project: "<YOUR PROJECT NAME>")— load prior review findings, recurring issues, and known patterns - Check LiveGuard memories: Read
.forge/liveguard-memories.jsonlif present — recent drift violations and incidents may flag known problem areas
--- PART A: CODE REVIEW ---
Review checklist:
- SCOPE COMPLIANCE — All changes within the Scope Contract?
- FORBIDDEN ACTIONS — Off-limits files/folders touched?
- ARCHITECTURE — Code follows layer separation?
- ERROR HANDLING — Proper error types, no empty catch blocks?
- NAMING — Follows project naming conventions?
- PATTERNS — Follows existing patterns from .github/instructions/?
- TESTING — New features covered by tests?
- SECURITY — Input validation? No secrets in code?
For each finding, assign: 🔴 Critical / 🟡 Warning / 🔵 Info
Output Part A:
| # | File | Finding | Severity | Rule Violated |
|---|
--- PART B: DRIFT DETECTION ---
Compare Scope Contract against actual changes:
- SCOPE CREEP — Work not in Scope Contract?
- UNPLANNED FILES — Files not in any Execution Slice?
- NON-GOAL VIOLATIONS — Work contradicting Out of Scope?
- FORBIDDEN ACTIONS — Off-limits touched?
- ARCHITECTURAL DRIFT — Patterns conflicting with instructions?
Output Part B:
| File | Issue | Violated Section |
|---|
--- COMBINED SUMMARY ---
- Code Review: Critical: N | Warnings: N | Info: N
- Drift Detection: Drift found: Yes/No (N issues)
- Verdict: PASS or FAIL (LOCKOUT)
Do NOT modify any files. Report only.
If the verdict is PASS and the phase is Small or Medium (≤5 slices), you may proceed to Step 6 (Ship) in this same session — Session 4 is optional for smaller features. For Large phases (6+ slices), a separate Session 4 is recommended to avoid context exhaustion.
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.
- today First seen · 111 lines · 23 tokens per session scan A 5f35d51c1ddd
step5-review-gate is a command published in the GitHub repository srnichols/plan-forge (5 stars, last pushed today), licensed MIT. It adds 23 tokens to every session and 1,189 once invoked, about $0.0001 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 2026-09-08.
Other commands, from other repositories
sdd-archive
Archive a completed SDD change — syncs specs and closes the cycle.
sdd-continue
Continue the next SDD phase in the dependency chain.
sdd-apply
Implement SDD tasks — writes code following specs and design.
sdd-status
Show structured SDD status for an active change.
sdd-verify
Validate implementation matches specs, design, and tasks.
sdd-ff
Fast-forward all SDD planning phases — proposal through tasks.