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/rodrigorjsf/prd-generator-plugin/prd-evolvegit clone --depth 1 https://github.com/rodrigorjsf/prd-generator-pluginWhat 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 | $0.00012 | $0.01757 |
| Opus 5 | $0.00006 | $0.00879 |
| Sonnet 5 | $0.00002 | $0.00351 |
| Haiku 4.5 | $0.00001 | $0.00176 |
Grade A, and why
prd-evolve 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 — 208 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/prd-evolve — PRD Evolution
You are orchestrating an incremental PRD evolution. You update ONLY the artifacts impacted by the described scope change, preserving all existing decisions that remain valid.
CRITICAL RULES:
- All generated/updated files MUST remain in English
- Do NOT regenerate artifacts that are unaffected by the change
- Every skill header must be updated with the new
prd_version - Respond to the user in whatever language they write
Input: $1 — description of what changed (required)
PHASE 0 — Read Current State
Create tasks: Delta Analysis / Research & Validation (if needed) / Artifact Updates / Commit
Pre-flight Check
Before reading any files, verify that docs/prd/PRD.md exists.
If it does NOT exist:
- Error: "No PRD found at docs/prd/PRD.md. Run
/prd-newfirst to generate the initial PRD." - Exit without modifying any files.
Read the following files:
docs/prd/PRD.md— extract current version from headerdocs/prd/ARCHITECTURE.mddocs/prd/ER.md(if exists).claude/skills/project-guardian/SKILL.md— readprd_versionfield.claude/skills/project-architecture/SKILL.md.claude/skills/project-domain-rules/SKILL.md.claude/skills/project-compliance/SKILL.md.claude/skills/project-cicd/SKILL.md(if exists) — readvcsandpipeline_filefrom frontmatter- Identify existing pipeline file: check for
.github/workflows/ci.yml,.gitlab-ci.yml,bitbucket-pipelines.yml
Check for stale skills: if any skill's prd_version < PRD's current version, warn the user that skills were already out of sync before this evolution.
PHASE 1 — Delta Analysis
Mark task "Delta Analysis" as in_progress.
Dispatch requirements-analyst agent with:
{
"mode": "delta",
"change_description": "$1",
"current_prd_summary": "<key sections from PRD.md>",
"current_architecture_summary": "<stack table + ADRs from ARCHITECTURE.md>"
}
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 · 208 lines · 12 tokens per session scan A 40a9ce9c0382
prd-evolve is a command published in the GitHub repository rodrigorjsf/prd-generator-plugin (2 stars, last pushed 6mo ago), licensed MIT. It adds 12 tokens to every session and 1,757 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.
constitution
Create or update the project constitution from interactive or provided principle inputs.
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.