Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add Sage-Bionetworks/agent-skills/plugin install agent-skillsWrote 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/sage-bionetworks/agent-skills/evolve-claudemd)<a href="https://agentmods.dev/skills/sage-bionetworks/agent-skills/evolve-claudemd"><img src="https://agentmods.dev/badge/skills/sage-bionetworks/agent-skills/evolve-claudemd/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/sage-bionetworks/agent-skills/evolve-claudemd"><img src="https://agentmods.dev/badge/skills/sage-bionetworks/agent-skills/evolve-claudemd.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 | $0.00038 | $0.01922 |
| Opus 5 | $0.00019 | $0.00961 |
| Sonnet 5 | $0.00008 | $0.00384 |
| Haiku 4.5 | $0.00004 | $0.00192 |
Grade A, and why
evolve-claudemd 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 11d 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.
How it starts
The opening of the file, as written. The whole thing — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Evolve CLAUDE.md
Update existing CLAUDE.md files by analyzing what changed in the codebase, GitHub, Jira, and Confluence since each file was last modified. Perform a full accuracy audit. Produce targeted, user-approved edits.
How this skill runs
This skill is an orchestrator. It keeps your (the top-level agent's) context lean by pushing work down two layers:
- Scripts (
scripts/*.sh) do the deterministic git/grep/parse plumbing and emit compact output. Run them; don't reimplement their logic inline. - Sub-agents (
claudemd-*agent types) do the context-heavy gathering — 100s of PRs, Jira/Confluence, deep source reads. They burn that raw data in their own context and return only short digests. Dispatch them; do not pull raw PR bodies, full Confluence pages, or whole source trees into this conversation yourself. - On-demand references (
references/*.md) hold the bulky rules/rubrics/templates. Read each only at the step that consumes it. - A PostToolUse write-guard hook validates every CLAUDE.md you write (no empty section headers). If it reports an issue, fix and rewrite.
Run the steps in order. Steps 2 and 5 dispatch sub-agents; Step 6 is the user-approval gate; nothing is written before approval.
Step 0 — Pre-flight
Run bash "${CLAUDE_PLUGIN_ROOT}"/skills/evolve-claudemd/scripts/preflight.sh. If it fails, stop and show its message. On success it prints the git remote= line — parse owner/repo from it for the GitHub sub-agent.
Step 1 — Discover
Run bash "${CLAUDE_PLUGIN_ROOT}"/skills/evolve-claudemd/scripts/discover.sh. It returns a JSON array (one record per CLAUDE.md: path, scope_dir, last_commit, last_date, commits_since, files_changed). Render a status table for the user:
| File | Last Updated | Commits Since | Files Changed |
|------|-------------|---------------|---------------|
Files with a null last_commit are uncommitted — audit against current state (see Edge Cases). If discover.sh returns [], warn the user there are no CLAUDE.md files and suggest /bootstrap-claudemd, then stop.
What ships with it
9 files 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.
- references/generation-rules.md 5.5 KB
- references/report-templates.md 2.9 KB
- references/scoring-rubric.md 2.5 KB
- scripts/claudemd-writeguard.sh 1.6 KB runs code
- scripts/discover.sh 1.9 KB runs code
- scripts/gather-code-changes.sh 3.0 KB runs code
- scripts/grep-hacks.sh 952 B runs code
- scripts/preflight.sh 651 B runs code
- scripts/verify-references.sh 3.3 KB runs code
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.
- 11d ago First seen · 115 lines · 38 tokens per session scan A aa2f08bd2622
evolve-claudemd is a skill published in the GitHub repository Sage-Bionetworks/agent-skills (5 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 38 tokens to every session and 1,922 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 2026-08-31.
Other skills, from other repositories
media-ingest
Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain. Multi-format handling with entity extraction and backlink propagation. Covers video-ingest, youtube-ingest, and book-ingest subtypes.
mem0-oss-to-platform
Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
memory
Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.
ha-data-stores
Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…
establishing-project-context
Use when the user asks to establish shared project language, or project work exposes a conflicting, renamed, or deprecated domain term that needs active semantic modeling. Routine small tasks stay on the fast path.