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/step1-preflight-check)<a href="https://agentmods.dev/commands/srnichols/plan-forge/step1-preflight-check"><img src="https://agentmods.dev/badge/commands/srnichols/plan-forge/step1-preflight-check.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 | $0.00033 | $0.01108 |
| Opus 5 | $0.00016 | $0.00554 |
| Sonnet 5 | $0.00007 | $0.00222 |
| Haiku 4.5 | $0.00003 | $0.00111 |
Grade A, and why
step1-preflight-check 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 — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Step 1: Pre-flight Check
Pipeline: Step 1 of 5 (Session 1 — Plan Hardening)
When: Before hardening any*-PLAN.md
Model suggestion: Any model / Copilot Auto (10% token savings) — checklist verification works well on all models
Next Step:step2-harden-plan.prompt.md
Replace <YOUR-PLAN> with your plan filename (without path or .md extension).
Act as a PRE-FLIGHT CHECK AGENT for plan hardening.
Pre-flight context check:
- Check OpenBrain (if configured):
search_thoughts("<plan topic> blockers", project: "<YOUR PROJECT NAME>")— load prior preflight failures and known blockers - Check LiveGuard memories: Read
.forge/liveguard-memories.jsonlif present — recent incidents or drift violations may indicate unresolved issues
Run these checks and report results. If any check fails, report the failure and do not proceed to Step 2.
-
GIT STATE — Run
git pull origin mainandgit status. Report: clean / dirty (list uncommitted files if dirty). -
ROADMAP LINK — Read docs/plans/DEPLOYMENT-ROADMAP.md. Confirm the phase for exists with a one-line goal. Report: ✅ found (quote the goal) / ❌ missing.
-
PLAN FILE — Confirm docs/plans/.md exists and is non-empty. Report: ✅ exists (N lines) / ❌ not found.
-
CORE GUARDRAILS — Confirm these files exist and are non-empty:
- .github/copilot-instructions.md
- .github/instructions/architecture-principles.instructions.md
- AGENTS.md Report: ✅ all present / ❌ missing (list which).
4b. AGENTIC FILES — Check if prompt templates, agent definitions, and skills exist:
- .github/prompts/ — list *.prompt.md files found (0 is OK for non-preset repos)
- .github/agents/ — list *.agent.md files found
- .github/skills/ — list */SKILL.md files found Report: ✅ N prompts, N agents, N skills found / ⚠️ none found (optional — won't block)
- DOMAIN GUARDRAILS — Scan .md for keywords to identify relevant domains.
For each domain detected, confirm the matching guardrail file exists:
- UI/Component/Frontend/Razor/React/Vue → .github/instructions/frontend.instructions.md (or blazor/react specific)
- Database/SQL/Repository/ORM/migration → .github/instructions/database.instructions.md
- API/Route/Controller/REST → .github/instructions/api-patterns.instructions.md
- Auth/OAuth/JWT/OIDC/session → .github/instructions/auth.instructions.md
- GraphQL/Schema/Resolver → .github/instructions/graphql.instructions.md
- Security/CORS/Secrets/Validation → .github/instructions/security.instructions.md
- Docker/K8s/deploy/CI → .github/instructions/deploy.instructions.md
- Test/spec/coverage → .github/instructions/testing.instructions.md Report: domains detected + guardrail status for each.
Output a summary table:
| Check | Result | Details |
|---|---|---|
| Git state | ✅/❌ | ... |
| Roadmap link | ✅/❌ | ... |
| Plan file | ✅/❌ | ... |
| Core guardrails | ✅/❌ | ... |
| Agentic files | ✅/⚠️ | ... |
| Domain guardrails | ✅/❌ | ... |
If ALL pass: "Pre-flight complete ✅ — proceed to Step 2 (Harden the Plan)" If ANY fail: "Pre-flight FAILED ❌" + list exactly what to fix.
Tip: For deeper diagnostics (environment tools, VS Code config, version currency, common problems), suggest running
pforge smith.
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 · 81 lines · 33 tokens per session scan A bf1fe1be6b25
step1-preflight-check is a command published in the GitHub repository srnichols/plan-forge (5 stars, last pushed today), licensed MIT. It adds 33 tokens to every session and 1,108 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 2026-09-08.
Other commands, from other repositories
quick-commit
A quick Git command for committing and pushing a small code change. Git is the tool that records code versions and sends them to a shared repository.
apex-git-commit
Stage everything except agent-output/, infra/, and .github/skills/sensei/ (unless on feat/skills-sensei), auto-generate a conventional commit, push, then prompt to open or update a PR. CLI-only (git + gh).
session-report
Capture what changed this session and why, scoped to the current branch. Read by ship verbs when synthesizing the commit message; deleted after a successful commit.
commit.en
Commit the current changes to Git.
afp
Prioritise feature - assigns ID, moves to backlog (shortcut for feature-prioritise).
explain
/explain Explain the last agent action (quick mode) /explain --verbose Full trace with file changes and decision rationale /explain --story STORY-XXX All actions for a story in chronological order /explain --agent Last action by a specific agent /explain --session All actions from a specific session /explain --diff…