wikiskill-evolve

wikiskill-evolve is a skill for Claude Code, Codex from ashutoshsinghpr7/wikiskill. It costs 48 tokens per session (666 once invoked), scanned A, original, MIT.

A process for improving an AI agent's reusable instructions from its past work. It turns session records into a shared knowledge base, proposes a revised skill, and keeps it only when testing shows it performs better than the current version.

In plain words
What is it for?
Use it to evolve agent skills, compare workspaces, test proposed changes, and transfer accepted skills between workspaces.
Why use it?
It provides a repeatable way to learn from failures and reject changes that do not improve results, rather than relying on guesswork.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: positional $N argument; mentions Claude Code; mentions Codex.

Good fit Use it to evolve agent skills, compare workspaces, test proposed changes, and transfer accepted skills between workspaces.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ashutoshsinghpr7/wikiskill/wikiskill-evolve
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 ashutoshsinghpr7/wikiskill --skill wikiskill-evolve
Clone the repo
git clone --depth 1 https://github.com/ashutoshsinghpr7/wikiskill

Made for: Claude Code, 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 wikiskill-evolve

README.md
[![agentmods](https://agentmods.dev/badge/skills/ashutoshsinghpr7/wikiskill/wikiskill-evolve.svg)](https://agentmods.dev/skills/ashutoshsinghpr7/wikiskill/wikiskill-evolve)
Your own site
<a href="https://agentmods.dev/skills/ashutoshsinghpr7/wikiskill/wikiskill-evolve"><img src="https://agentmods.dev/badge/skills/ashutoshsinghpr7/wikiskill/wikiskill-evolve.svg" alt="Measured on agentmods" height="20"></a>
Per session 48 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 666 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00048 $0.00666
Opus 5 $0.00024 $0.00333
Sonnet 5 $0.00010 $0.00133
Haiku 4.5 $0.00005 $0.00067

Measured 2d ago against content hash 521054c5993d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

wikiskill-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 2d 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/wikiskill-evolve/SKILL.md · 69 lines

How it starts

The opening of the file, as written. The whole thing — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.

WikiSkill Evolve

Run Google's WikiSkill evolution loop (arXiv:2608.27454) — a faithful implementation with Hermes as the reference backend. The agent evolves its own skills: raw sessions → a maintainer distills failure patterns into a persistent wiki → a proposer writes a candidate skill → a validation gate accepts it only if R_val > R_best (git rollback otherwise).

When to use

  • You want an agent's own experience (traces) turned into reusable skills
  • You want to test whether a candidate skill actually helps, with statistics instead of vibes
  • You're running the paper's protocol on your own tasks

Install

pip install wikiskill          # Python ≥ 3.10; works with Hermes, Claude Code

Run the loop

wikiskill init myws                        # workspace + auto-graded bench
wikiskill evolve myws --iters 3            # train → maintain → propose → gate
wikiskill status myws                      # baseline, r_best, skill state
wikiskill compare wsA wsB --iters 5        # paired exact-binomial comparison
wikiskill transfer src dst                 # copy accepted skills to another ws

Reading the output

  • runs/state.jsonbaseline (S₀ on val), r_best, next_iter
  • wiki/log.md — every maintenance/proposal/gate decision with evidence
  • wiki/patterns/ — distilled failure patterns (the raw material)
  • wiki/skill-impact.md — rejected proposals stay visible (paper requirement)
  • Gate verdicts: ACCEPTED (R_val > R_best, git commit), REJECTED (rolled back), no_action (proposer declined — a valid outcome)

Backends

wikiskill init myws --backend claude       # Claude Code as the worker

Hermes is the reference backend; Claude Code ships in the box; codex/opencode are on the roadmap. All speak open SKILL.md, so evolved skills transfer.

Honest-expectation notes

  • Each iteration costs ~$0.09 on free-tier models (gemini-lite class) — turn budgets and --max-turns bound the spend
  • A weak model may produce no_action iterations — that's the gate working, not a failure; skill accumulation needs a reasonably strong proposer
  • The gate has rejected harmful skills in live runs — a rejection is a win

Read the full file on GitHub · 69 lines

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. 2d ago First seen · 69 lines · 48 tokens per session scan A 521054c5993d

Subscribe to this mod's changes

wikiskill-evolve is a skill published in the GitHub repository ashutoshsinghpr7/wikiskill (117 stars, last pushed 6d ago), licensed MIT. It adds 48 tokens to every session and 666 once invoked, about $0.0002 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 2026-09-05.

Related

Other skills, from other repositories