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.
npx agentmods add commands/marcmallet/specforge/prgit clone --depth 1 https://github.com/marcmallet/specforgeWhat 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 | $0.00011 | $0.00898 |
| Opus 5 | $0.00005 | $0.00449 |
| Sonnet 5 | $0.00002 | $0.00180 |
| Haiku 4.5 | $0.00001 | $0.00090 |
Grade A, and why
pr 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 yesterday.
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 — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are helping generate a pull request description for a completed feature.
The user input is: $ARGUMENTS
Parse the ticket number from the input (e.g. "PROJ-0001").
Specs directory
Read the project config at: @.claude/specforge/config.json
If the file exists, use the value of the specsDir field as the base directory.
If the file does not exist, fall back to .claude/specforge/ inside the current project.
The full path for this ticket is: //
Read the feature files
Read the following files:
- Spec: //spec.md (REQUIRED)
- Plan: //plan.md (REQUIRED)
- Review: //review.md (OPTIONAL — skip spec coverage section if missing)
If spec or plan are missing, fail gracefully with a clear error message telling the user which files are required.
Generate the PR description
Using the spec, plan, and review files, create a structured PR description with these sections:
1. Title
Derive from the spec's feature name (e.g. "Feature: PR Overview Command" → "Add PR Overview Command") Keep it concise (under 70 characters).
2. Summary (2-3 sentences)
- What does this feature do and why does it exist? (take from spec Overview section)
3. Changes
Summarize what was done, grouped by the plan's task tags:
- Backend: (summarize [backend] tasks from the plan)
- Frontend: (summarize [frontend] tasks from the plan)
- Shared: (summarize [both] tasks from the plan)
If the plan lists specific files in its "Files to Create or Modify" section, include those. Otherwise summarize the types of changes.
4. Spec Coverage (if review.md exists)
Pull the key findings from the review file:
- What acceptance criteria were met?
- Any coverage gaps or caveats flagged by the review?
- Keep this section brief (2-3 bullets max)
If review.md does NOT exist, add a note: "Note: No review has been run yet. You may want to run /specforge:review <ticket-number> before merging."
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.
- yesterday First seen · 110 lines · 11 tokens per session scan A 24c7370cc7db
pr is a command published in the GitHub repository marcmallet/specforge (9 stars, last pushed 4mo ago), licensed MIT. It adds 11 tokens to every session and 898 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 2026-08-31.
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.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
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.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.