Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/srnichols/plan-forgenpx agentmods add commands/srnichols/plan-forge/step6-shipWrote 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/step6-ship)<a href="https://agentmods.dev/commands/srnichols/plan-forge/step6-ship"><img src="https://agentmods.dev/badge/commands/srnichols/plan-forge/step6-ship.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 | $0.00026 | $0.01337 |
| Opus 5 | $0.00013 | $0.00668 |
| Sonnet 5 | $0.00005 | $0.00267 |
| Haiku 4.5 | $0.00003 | $0.00134 |
Grade A, and why
step6-ship 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 — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Step 6: Ship
Pipeline: Step 6 of 6 (Session 4 — Ship) When: After the Review Gate passes (Step 5) Model suggestion: Any model / Copilot Auto (10% token savings) — commit, roadmap update, and postmortem are straightforward Prerequisite: Step 5 verdict must be PASS
Replace <YOUR-HARDENED-PLAN> with your hardened plan filename.
Read these files first:
- docs/plans/.md (Definition of Done + Execution Slices)
- docs/plans/DEPLOYMENT-ROADMAP.md
- .github/instructions/git-workflow.instructions.md
Plan Forge maintainers shipping a framework release (i.e., bumping the
pforgeversion itself, not just closing a project phase): follow docs/RELEASE-CHECKLIST.md instead of this prompt. The checklist covers VERSION/package.json sync, hooks mirror, instruction enumeration, the mandatorygh release createstep, and bump-back-to-dev.
Now act as a SHIPPING AGENT. The Review Gate has passed — your job is to finalize and close out this phase.
1. VERIFY REVIEW PASSED
Confirm that the Review Gate (Step 5) issued a PASS verdict. If the verdict was LOCKOUT or unknown, direct me back to Step 5 before proceeding.
2. COMMIT
- Run
git status— list all changed/created files - Run
git diff --stat— summarize scope of changes - Read the hardened plan's phase name and goal
- Generate a conventional commit message:
- Type:
feat/fix/refactor(based on phase type) - Scope: derived from phase name
- Body: list execution slices completed
- Type:
- Show the proposed commit message and ask for confirmation
- Run
git add -Athengit commit -m "<message>"
3. UPDATE ROADMAP
- Read
docs/plans/DEPLOYMENT-ROADMAP.md - Find the entry for this phase
- Update status from 🚧 (or 📋) to ✅ Complete
- Commit:
docs(roadmap): mark Phase N complete
4. CAPTURE POSTMORTEM
Compile a brief postmortem and append it to the plan file as a ## Postmortem section:
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 · 131 lines · 26 tokens per session scan A 5f6aa5bcc82d
step6-ship is a command published in the GitHub repository srnichols/plan-forge (5 stars, last pushed today), licensed MIT. It adds 26 tokens to every session and 1,337 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
arrange-workspace-flow-choose-workspace-layout
Phase 1 Choose Workspace Layout of arrange-workspace-flow.
afcl
Close feature [agent] [--adopt] - merges branch, cleans up, optionally adopts from losers (shortcut for feature-close).
afp
Prioritise feature - assigns ID, moves to backlog (shortcut for feature-prioritise).
orc
Parallel multi-agent orchestration for complex features.
parallel-task
Execute bulk modifications across codebase with parallel agents and safety guarantees.
ship
Encodes the "stage and commit" ritual: verify (receipt gate) → scope → branch → write the commit message from what is actually staged → commit → push → open PR to the default branch → move the Jira issue to In Review. NO merge (merging is the reviewer's call). NO tag (deploys are project-specific and out of scope).