pm-evolve-skills

pm-evolve-skills is a skill for Codex from joinwell52-AI/CodeFlowMu-open. It costs 59 tokens per session (765 once invoked), scanned A, original, MIT.

A process for finding and learning capabilities that a product manager is missing. It checks available tools, skills, documentation, code, and examples, then validates the chosen approach with a small practical test.

In plain words
What is it for?
Use it when a request involves a new domain, MCP capability, skill, tool, workflow, or stronger proof than the product manager can currently provide.
Why use it?
It reduces the risk of guessing when a task needs unfamiliar knowledge, tools, permissions, or evidence. It creates a traceable path from identifying the gap to applying and checking a solution.

Skill for Codex

Written for Codex: agents/openai.yaml present.

Good fit Use it when a request involves a new domain, MCP capability, skill, tool, workflow, or stronger proof than the product manager can currently provide.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/joinwell52-ai/codeflowmu-open/pm-evolve-skills
Install

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.

Any agent
npx skills add joinwell52-AI/CodeFlowMu-open --skill pm-evolve-skills
Clone the repo
git clone --depth 1 https://github.com/joinwell52-AI/CodeFlowMu-open

Made for: Codex.

Wrote 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.

agentmods badge for pm-evolve-skills

README.md
[![agentmods](https://agentmods.dev/badge/skills/joinwell52-ai/codeflowmu-open/pm-evolve-skills/github.svg)](https://agentmods.dev/skills/joinwell52-ai/codeflowmu-open/pm-evolve-skills)
Your own site
<a href="https://agentmods.dev/skills/joinwell52-ai/codeflowmu-open/pm-evolve-skills"><img src="https://agentmods.dev/badge/skills/joinwell52-ai/codeflowmu-open/pm-evolve-skills/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.

agentmods 80×15 button for pm-evolve-skills

Your own site · 80×15
<a href="https://agentmods.dev/skills/joinwell52-ai/codeflowmu-open/pm-evolve-skills"><img src="https://agentmods.dev/badge/skills/joinwell52-ai/codeflowmu-open/pm-evolve-skills.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 59 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 765 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00059 $0.00765
Opus 5 $0.00030 $0.00382
Sonnet 5 $0.00012 $0.00153
Haiku 4.5 $0.00006 $0.00076

Measured 9d ago against content hash 23c6b348afc7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

pm-evolve-skills 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 9d 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.

skills/pm-evolve-skills/SKILL.md · 70 lines

How it starts

The opening of the file, as written. The whole thing — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.

PM Skill Evolution

Treat capability gaps as work to resolve, not as a reason to guess or immediately hand the problem back to ADMIN.

Workflow

  1. State the required capability precisely. Distinguish missing knowledge, missing procedure, missing tool access, and missing permission.
  2. Inventory what is already available:
    • MCP tools and their schemas.
    • .codeflowmu/agent-skills.manifest.json.
    • Relevant skills/*/SKILL.md packages.
    • Repository code, tests, docs, examples, and prior evidence.
    • Use skill_search to search the local library, GitHub, and the public web when the capability is not already known.
  3. Select the smallest credible learning source. Prefer source code, tests, official documentation, and proven local examples.
  4. Load only the relevant Skill or documentation. Do not flood context with the whole catalog.
    • Use skill_learn with selected local skill ids and source URLs to build a traceable learning pack.
  5. Learn by doing: run a minimal experiment, build a small example, inspect a real artifact, or execute a reversible probe.
  6. Verify the result against an explicit expectation. Record failures and uncertainty honestly.
  7. Apply the capability to the current problem.
  8. Retain reusable learning:
    • Update or create a focused Skill when the procedure will recur.
    • Add a template or example when structure matters.
    • Record a proposal when installation, permission, or architectural change requires approval.
    • Use skill_publish only after a real validation succeeds. Include validation evidence and source URLs; do not overwrite an existing Skill implicitly.
  9. Reuse retained knowledge on later tasks instead of rediscovering it.

Product / UI capability gaps

Weak product planning is a capability gap. If PM cannot confidently define product positioning, user value, information architecture, interaction flow, visual direction, mobile/PWA/Gateway delivery boundary, or acceptance evidence, PM must:

  1. Load pm-product-design-brief.
  2. Check the relevant UI playbook packages:
    • ui-requirements
    • ui-information-architecture
    • ui-visual-consistency
    • ui-usability-acceptance
  3. Inspect nearby successful product examples or reports before dispatch.
  4. Produce a concrete design brief, then dispatch DEV / QA / OPS.
  5. If the pattern will recur, refine the Playbook or create a smaller reusable template after validation.

Read the full file on GitHub · 70 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

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.

  1. 9d ago First seen · 70 lines · 59 tokens per session scan A 23c6b348afc7

Subscribe to this mod's changes

pm-evolve-skills is a skill published in the GitHub repository joinwell52-AI/CodeFlowMu-open (2 stars, last pushed 15d ago), licensed MIT. It adds 59 tokens to every session and 765 once invoked, about $0.0003 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.