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 skills add AgentToolkit/altk-evolve --skill evolve-lite-unpublishgit clone --depth 1 https://github.com/AgentToolkit/altk-evolveWrote 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/agenttoolkit/altk-evolve/evolve-lite-unpublish)<a href="https://agentmods.dev/skills/agenttoolkit/altk-evolve/evolve-lite-unpublish"><img src="https://agentmods.dev/badge/skills/agenttoolkit/altk-evolve/evolve-lite-unpublish/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.
<a href="https://agentmods.dev/skills/agenttoolkit/altk-evolve/evolve-lite-unpublish"><img src="https://agentmods.dev/badge/skills/agenttoolkit/altk-evolve/evolve-lite-unpublish.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00023 | $0.00316 |
| Opus 5.5 | $0.00009 | $0.00126 |
| Sonnet 5.5 | $0.00005 | $0.00063 |
| Haiku 4.5 | $0.00002 | $0.00032 |
Grade A, and why
evolve-lite:unpublish 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- unpublish — 98% identical, 10 lines differ
What it actually says
Unpublish an Entity
Read evolve.config.yaml. Select a write-scope repo and a published
{type}/{filename} owned by identity.user. Ask which repo if ambiguous.
Explain that unpublishing removes the current shared copy after pushing; it
does not erase git history or copies already downloaded by subscribers.
Run:
python3 .bob/skills/evolve-lite-unpublish/scripts/unpublish.py --entity "{filename}" --type "{type}" --repo "{repo}" --user "{identity.user}"
The script restores a private entity before removing the shared file. It refuses unknown or different owners, and refuses to overwrite an existing private mirror. If a mirror exists, compare the two and reconcile them with the user before retrying; do not delete either copy blindly.
Stage only the selected deletion and publish it:
git -C ".evolve/entities/subscribed/{repo}" add -- "{type}/{filename}"
git -C ".evolve/entities/subscribed/{repo}" commit -m "[evolve] unpublish: {filename}"
git -C ".evolve/entities/subscribed/{repo}" push origin "{branch}"
Use the configured branch (default main). For a rejected push follow the
non-fast-forward recovery workflow in evolve-lite:publish. Report
success only after pushing. Retain the restored private copy on push failure.
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.
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 · 35 lines · 23 tokens per session scan A adffd9945a12
evolve-lite:unpublish is a skill published in the GitHub repository AgentToolkit/altk-evolve (131 stars, last pushed today), licensed Apache-2.0. It adds 23 tokens to every session and 316 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-10-22.
Other skills, from other repositories
commit
Automatically analyzes code changes and creates git commits with conventional commit messages when the user indicates they want to save their work, commit changes, or says 'commit this', 'save my changes', 'let's commit'. Auto-detects commit type, scope, and ticket reference from branch name.
branch-and-worktree-workflow
Isolates feature work in its own branch or worktree and integrates it cleanly when done. Use this when starting work that should not disturb the current workspace, when several efforts must proceed in parallel on one repository, or when implementation is finished and the change needs merging, rebasing, or splitting…
unslop-commit
Rewrites commit messages so they sound like a careful human engineer wrote them. Strips AI/marketing slop ("comprehensive solution", "robust implementation", "leverage", "enhance", "seamlessly", "This commit..."). Keeps Conventional Commits format. Subject ≤72 chars (aim ≤50), imperative mood. Body only when "why"…
precommit
Pre-commit checks — lint:fix -> build -> test.
next-step
Change-aware next step advisor. Use when: user asks what to do next, workflow progression is unclear, session just started with dirty worktree. Not for: executing the suggested command (user decides), auto-loop decisions (hooks handle that). Output: findings-based suggestions or session summary with commit seed.
precommit-fast
Quick pre-commit checks — lint:fix -> test.