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/step0-specify-feature)<a href="https://agentmods.dev/commands/srnichols/plan-forge/step0-specify-feature"><img src="https://agentmods.dev/badge/commands/srnichols/plan-forge/step0-specify-feature/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/commands/srnichols/plan-forge/step0-specify-feature"><img src="https://agentmods.dev/badge/commands/srnichols/plan-forge/step0-specify-feature.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 | $0.00034 | $0.03834 |
| Opus 5.5 | $0.00014 | $0.01534 |
| Sonnet 5.5 | $0.00007 | $0.00767 |
| Haiku 4.5 | $0.00003 | $0.00383 |
Grade A, and why
step0-specify-feature 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 11d 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 — 352 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Step 0: Specify Feature
Pipeline: Step 0 (optional, recommended) — Run before Steps 1–5
Model suggestion: Claude (best at conversational interviews and ambiguity detection)
When: You have a rough idea for a feature but haven't written a plan yet
Next Step: Write a*-PLAN.md, thenstep1-preflight-check.prompt.md
Output: A specification section to include as front matter in your Phase Plan
Replace <FEATURE-NAME> with a short name for the feature you're building.
Act as a SPECIFICATION AGENT helping me define before any technical planning begins.
Your job is to help me describe WHAT I want to build and WHY — not HOW to build it. Ask me structured questions to surface requirements I may not have thought about. For anything I'm unsure of, tag it with [NEEDS CLARIFICATION: description] — these markers MUST be resolved before the plan can be hardened (Step 2 will block on them).
FIRST: Check for Prior Context
-
Check OpenBrain (if configured):
search_thoughts("<FEATURE-NAME>", project: "<YOUR PROJECT NAME>")— load prior decisions, gotchas, and lessons about this feature area. If results found, reference them in the specification. -
Check LiveGuard memories: Read
.forge/liveguard-memories.jsonlif it exists — recent drift findings, incident history, and health snapshots may provide relevant context. -
Check Spec Kit Artifacts:
Before asking any questions, scan the project for Spec Kit artifacts:
- Check if
specs/directory exists (Spec Kit feature directory) - Check if
memory/constitution.mdexists (Spec Kit project constitution) - Check if any
specs/*/spec.mdorspecs/*/plan.mdfiles exist
If Spec Kit artifacts are found:
"I found Spec Kit artifacts in this project:
specs/<feature>/spec.md— feature specificationspecs/<feature>/plan.md— implementation planmemory/constitution.md— project constitutionPlan Forge can import these directly:
- Import spec → Skip the interview, map spec.md sections to Plan Forge format
- Import plan → Convert plan.md into a hardened execution contract (Phase Plan)
- Import constitution → Convert to
docs/plans/PROJECT-PRINCIPLES.md- Start fresh → Ignore Spec Kit files and run the full interview
Which would you like?"
CLI shortcut:
pforge crucible import --from=spec-kitruns all four import steps non-interactively and emits a ready-to-run Phase Plan with Crucible frontmatter already applied.
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.
- 11d ago Changed · +25 lines 97f4183e7d3b
- 1mo ago First seen · 327 lines · 34 tokens per session scan A 72dc8f2272db
step0-specify-feature is a command published in the GitHub repository srnichols/plan-forge (6 stars, last pushed today), licensed MIT. It adds 34 tokens to every session and 3,834 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 2026-09-08.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
speckit.bug.fix
Apply the remediation from a bug assessment and record what was changed.
speckit.bug.test
Validate that a previously fixed bug is resolved and record the verification report.