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 commands/sdsrss/claudemd/claudemd-refreshgit clone --depth 1 https://github.com/sdsrss/claudemdWrote 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/commands/sdsrss/claudemd/claudemd-refresh)<a href="https://agentmods.dev/commands/sdsrss/claudemd/claudemd-refresh"><img src="https://agentmods.dev/badge/commands/sdsrss/claudemd/claudemd-refresh.svg" alt="Measured on agentmods" 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 | $0.00070 | $0.00320 |
| Opus 5 | $0.00035 | $0.00160 |
| Sonnet 5 | $0.00014 | $0.00064 |
| Haiku 4.5 | $0.00007 | $0.00032 |
Grade A, and why
claudemd-refresh scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Usage: /claudemd-refresh
Run: bash "${CLAUDE_PLUGIN_ROOT}/scripts/refresh-plugin.sh"
On success, tell the user: restart Claude Code (or /reload-plugins). Nothing else is needed — the first new session auto-runs install.js (SessionStart bootstrap / version-sync hook) to sync ~/.claude spec + manifest; /claudemd-install is NOT part of this flow. Suggest verifying afterwards with /claudemd-status (installed == latest).
If the user has other Claude Code windows open, tell them to run /reload-plugins in each one too. The refresh removes the old versioned plugin-cache dir, but every already-running session pinned its hook paths to that dir at startup — those sessions error on every hook event (claudemd enforcement is absent) until they reload or restart.
If the script fails with 'claude' CLI not found, have the user paste the manual sequence one line at a time:
/plugin marketplace update claudemd
/plugin uninstall claudemd@claudemd
/plugin install claudemd@claudemd
/reload-plugins
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.
- 4d ago First seen · 22 lines · 70 tokens per session scan A e5a9bd465f1f
claudemd-refresh is a command published in the GitHub repository sdsrss/claudemd (2 stars, last pushed 11d ago), licensed MIT. It adds 70 tokens to every session and 320 once invoked, about $0.0003 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 commands, from other repositories
brooks-debt
Run a Brooks-Lint tech debt assessment.
brooks-health
Run a Brooks-Lint codebase health dashboard across all four dimensions.
plan
Turn an approved spec into an implementation plan an engineer with zero context could execute — with a quality controller that blocks placeholders and hollow tasks.
simplify
The over-engineering review: five tags (delete, stdlib, native, yagni, shrink), a mandatory replacement per finding, and a real null result when there is nothing to cut.
audit
Onboard an existing codebase: every domain's checks over the whole tree, then a triaged plan to bring it in line.
git
The pre-finish status: branch, hygiene findings, message checks, workflow lint, template state.