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 skills/godshiba/genesis/learnnpx skills add godshiba/genesis --skill learngit clone --depth 1 https://github.com/godshiba/genesisWrote 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/skills/godshiba/genesis/learn)<a href="https://agentmods.dev/skills/godshiba/genesis/learn"><img src="https://agentmods.dev/badge/skills/godshiba/genesis/learn.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 | $0.00080 | $0.00487 |
| Opus 5 | $0.00040 | $0.00244 |
| Sonnet 5 | $0.00016 | $0.00097 |
| Haiku 4.5 | $0.00008 | $0.00049 |
Grade A, and why
learn 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 4d 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.
What it actually says
/genesis:learn — Fold Lessons Back Into the System
GENESIS is designed to evolve. A rule a project repeatedly violates is wrong for that project; a pattern three projects repeat belongs in the template. This skill is the mechanism.
Steps
-
Gather evidence. Read the project's registries — SESSION_LOG (what actually happened), LANDMINES (what surprised us), ISSUES (what recurred), DECISIONS (what we chose) — plus recent git history. Look for:
- A landmine category that appeared 2+ times: candidate for a CLAUDE.md invariant or key pattern.
- A gate that produced friction without payoff in this project: candidate for a recorded, deliberate deviation.
- A convention followed in code but written nowhere: candidate for the CLAUDE.md Key Patterns section.
- A workflow improvement any project would want: candidate for upstream.
-
Classify each finding by destination:
- Project-level: edit this project's CLAUDE.md (invariants, patterns, doc-sync map). Apply directly after listing the proposed edits.
- Deviation: record in DECISIONS.md why this project bends a GENESIS rule. The rule stands elsewhere.
- Upstream: belongs in the GENESIS plugin itself (templates, doctrine, a skill). The installed plugin is a read-only cache — do not edit it. Instead, produce the exact proposed diff against the plugin repo (https://github.com/godshiba/genesis) and offer to apply it if the user has a local clone, or format it as a PR-ready change.
-
Report: findings, destination for each, and what was applied vs proposed. Keep it short — three strong findings beat ten weak ones. Zero findings is a valid result; say so rather than inventing lessons.
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.
- 4d ago First seen · 39 lines · 80 tokens per session scan A 1fedc15acbdd
learn is a skill published in the GitHub repository godshiba/genesis (2 stars, last pushed 2mo ago), licensed MIT. It adds 80 tokens to every session and 487 once invoked, about $0.0004 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 skills, from other repositories
to-plan
Capture the chat into .task/task/ .md with ## Description plus ## Plan (Goal/Touches/Logic) — the deepest one-task capture.
roadmap-to-workflow
Fan an approved .task/roadmap/ .md out to a dynamic Workflow — parallel planning, serialized implementation, dependency-ordered waves.
self-improve
Self-improve this skills repo — surface and (safely) apply quality improvements across four parallel read-only lenses (Clarity, Leanness, Coverage, Ergonomics). Sibling of /self-audit — audit fixes rule violations, improve raises quality where no rule is broken. Local meta-skill, independent of the /task: pipeline.
to-roadmap
Capture a multi-task initiative into .task/roadmap/ .md — a phase-grouped backlog of ready-to-pick-up items.
to-task
Capture the chat (or a roadmap item) into .task/task/ .md — ## Description only, no ## Plan.
self-audit
Self-audit this skills repo against CLAUDE.md invariants, the artifact contract, and README/CLAUDE.md/docs sync via three parallel read-only subagents. Local meta-skill — independent of the /task: pipeline.