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/agenttoolkit/altk-evolve/doctornpx skills add AgentToolkit/altk-evolve --skill doctorgit clone --depth 1 https://github.com/AgentToolkit/altk-evolveWhat 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 | $0.00027 | $0.00400 |
| Opus 5 | $0.00014 | $0.00200 |
| Sonnet 5 | $0.00005 | $0.00080 |
| Haiku 4.5 | $0.00003 | $0.00040 |
Grade A, and why
doctor 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.
What it actually says
Doctor
Overview
On Claude, evolve is delivered by a single @.evolve/EVOLVE.md import line in
this repo's ./CLAUDE.md. That import requires a one-time, per-project "allow
external imports" approval. If you (or a teammate) declined it — even once, in a
past session — Claude silently disables the import forever, the thin EVOLVE.md
never loads, and evolve becomes a no-op with no error.
This skill checks whether the import is actually reaching your sessions, by looking for a canary token that the installed EVOLVE.md expands into the session transcript when the import loads.
Required Action
Run the doctor script from the repo root:
python3 ${CLAUDE_PLUGIN_ROOT}/skills/evolve-lite/doctor/scripts/doctor.py
It is read-only and always exits 0. Read the status code it prints:
- OK — the import is loading; nothing to do.
- IMPORT_DISABLED — the
@importline is inCLAUDE.mdbut its content is not reaching sessions (you likely declined the external-import approval). Follow the remediation the script prints: purge the project approval, start a new session, and Allow the import dialog. - NOT_INSTALLED — evolve isn't wired into this repo; re-run the installer.
- STALE_EVOLVE_MD — the installed
.evolve/EVOLVE.mdpredates the canary; re-run the installer to refresh it. - UNKNOWN — no recent Claude transcripts for this project yet; open a session, then re-run.
Relay the status and any remediation to the user.
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.
- 2d ago First seen · 44 lines · 27 tokens per session scan A 0bd089b39a39
doctor is a skill published in the GitHub repository AgentToolkit/altk-evolve (105 stars, last pushed 7d ago), licensed Apache-2.0. It adds 27 tokens to every session and 400 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 2026-08-30.
Other skills, from other repositories
agent-recall
Persistent compounding memory for AI agents. 5 default MCP tools: sessionstart, sessionend, remember, recall, check. Full surface (18 tools) available with --full flag. Two-verb model: inhale (sessionstart) and exhale (sessionend). Correction-first memory with decision trail tracking, watchfor warnings, palace rooms…
shelve
Offload a closed conversation topic (or a whole imported dialog) to the memory shelf as a Markdown episode with a validated digest. Use when a topic is finished, when context grows heavy, before compaction, or when the user asks to shelve/archive part of the conversation. M0 prompt-only version — the agent does the…
speckit-tasks
Generate an actionable, dependency-ordered tasks.md for the feature based on available design artifacts.
speckit-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.
speckit-implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.
speckit-taskstoissues
Convert existing tasks into actionable, dependency-ordered GitHub issues for the feature based on available design artifacts.