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/subscribenpx skills add AgentToolkit/altk-evolve --skill subscribegit 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 | $0.00025 | $0.00548 |
| Opus 5 | $0.00013 | $0.00274 |
| Sonnet 5 | $0.00005 | $0.00110 |
| Haiku 4.5 | $0.00003 | $0.00055 |
Grade A, and why
subscribe 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.
This is a copy
95% identical to evolve-lite:subscribe — 11 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
What it actually says
Subscribe to a Shared Repo
Overview
Configured guidelines repos are multi-reader / multi-writer git databases,
described in a single unified list in evolve.config.yaml:
repos:
- name: memory
scope: write
remote: [email protected]:alice/evolve.git
branch: main
notes: public memory for foobar project
- name: org-memory
scope: read
remote: [email protected]:acme/org-memory.git
branch: main
notes: private memory shared only within my org
scope: read— download-only. Synced on every run.scope: write— publish target. Synced on every run too, so you see what you have already published and anything others have pushed.
Workflow
Step 1: Bootstrap config if missing
If evolve.config.yaml does not exist, ask the user for a username and
create:
identity:
user: {username}
repos: []
sync:
on_session_start: true
Also ensure .evolve/ is gitignored:
grep -qxF '.evolve/' .gitignore 2>/dev/null || echo '.evolve/' >> .gitignore
Step 2: Gather details
Ask the user for:
- the remote URL for the guidelines repo
- a short local name such as
alice - the scope:
read(default, subscribe-only) orwrite(also a publish target) - an optional note
Step 3: Run subscribe script
python3 ${CLAUDE_PLUGIN_ROOT}/skills/evolve-lite/subscribe/scripts/subscribe.py \
--name "{name}" \
--remote "{remote}" \
--branch main \
--scope "{scope}" \
--notes "{notes}"
Step 4: Confirm
Tell the user the repo was added and they can run /evolve-lite:sync
immediately if they want to pull updates now.
Notes
- The repo is cloned directly into
.evolve/entities/subscribed/{name}/, which doubles as the recall mirror - Subscribed entities will appear in recall with
[from: {name}]annotations - Read-scope repos use a shallow clone; write-scope repos use a full clone so publish commits can be rebased and pushed cleanly
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 · 85 lines · 25 tokens per session scan A 8f4c8c0589bc
subscribe is a skill published in the GitHub repository AgentToolkit/altk-evolve (105 stars, last pushed 7d ago), licensed Apache-2.0. It adds 25 tokens to every session and 548 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 95% identical to evolve-lite:subscribe, differing in 11 lines, and is treated as a copy.
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-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.
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.