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/pekral/cursor-rules/refresh-claude-mdnpx skills add pekral/cursor-rules --skill refresh-claude-mdgit clone --depth 1 https://github.com/pekral/cursor-rulesWrote 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/pekral/cursor-rules/refresh-claude-md)<a href="https://agentmods.dev/skills/pekral/cursor-rules/refresh-claude-md"><img src="https://agentmods.dev/badge/skills/pekral/cursor-rules/refresh-claude-md.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 | $0.00066 | $0.01152 |
| Opus 5 | $0.00033 | $0.00576 |
| Sonnet 5 | $0.00013 | $0.00230 |
| Haiku 4.5 | $0.00007 | $0.00115 |
Grade A, and why
refresh-claude-md 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 today.
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 — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Constraints
- Apply
@rules/php/core-standards.mdc - Apply
@rules/git/general.mdc - Trigger only to update or create
CLAUDE.md— never run this as a general onboarding or audit task - Reconnaissance uses Glob and Grep; use Read only to resolve an ambiguous signal, never to read every file
- Enhance, never blindly replace: preserve all human-authored sections, custom rules, and project-specific instructions already in
CLAUDE.md - Keep
CLAUDE.mdscannable and under ~100 lines; link to@rules/**instead of pasting rule content - Flag unknowns explicitly ("Could not determine X") rather than speculate
- Do not modify other skills, rules, or production code
Use when
CLAUDE.mddoes not exist and the project needs one generated from the codebaseCLAUDE.mdis stale — the tech stack, build/test commands, directory layout, or conventions have drifted from what the file documents- The user asks to "refresh", "regenerate", "update", or "rebuild"
CLAUDE.md - A dependency, framework, or tooling change has invalidated the documented commands or structure
Do not use this skill for ad-hoc codebase questions, code review, or onboarding write-ups — it has one job: keep CLAUDE.md correct.
Execution
1. Decide whether a refresh is warranted
- Read the existing
CLAUDE.md(if any) and record which sections are human-authored vs auto-generated. - Confirm at least one trigger applies. If
CLAUDE.mdalready matches the codebase, stop and report "no refresh needed" instead of rewriting it.
2. Reconnaissance (Glob + Grep only)
Gather signals without reading every file:
- Manifests —
composer.json,package.json,go.mod,pyproject.toml,Cargo.toml,Gemfile, etc. - Framework fingerprint — Laravel (
artisan,bootstrap/app.php),vite.config.*,next.config.*, and similar config files - Entry points —
public/index.php,artisan,app.*,main.*,src/roots,routes/ - Directory snapshot — top two levels, excluding
vendor,node_modules,.git,dist,build,storage - Tooling —
phpstan.neon,pint.json,rector.php,phpcs.xml,.github/workflows/,Dockerfile,.env.example - Tests —
tests/,*Test.php,*.spec.ts, Pest/PHPUnit config
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.
- today First seen · 68 lines · 66 tokens per session scan A a45f24adc13b
refresh-claude-md is a skill published in the GitHub repository pekral/cursor-rules (6 stars, last pushed 4d ago), licensed MIT. It adds 66 tokens to every session and 1,152 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 2026-09-03.
Other skills, from other repositories
retro
CP-7 retrospective: audit checkpoints, evidence quality, action items, and harvest candidates. Closes the V-model cycle and feeds the next run. Use via /retro after ship, escalate, or significant session.
pad
Talk to your project. Natural-language project management — create items, check status, plan work, brainstorm ideas, and more.
quality-engineering-zephyr-coverage-analysis
Audit test coverage health, gaps, and QE debt for Jira stories or epics. Produces coverageanalysisreport.md with AC-to-TC heatmap, risk scores, and prioritized action plan. Use when assessing coverage percentage, pre-release readiness, sprint readiness, or identifying missing test cases. Do NOT use for TC creation …
pm-init
Skill "pm-init" from wei63w/pm-manager, covering user input, outline, 1. scaffold, 2. lifecycle and type and 3. detect spec kit (required).
fde
Keeps the engagement record for client work. Use when they name a client or stakeholder. Use when they debrief a meeting or paste notes. Use when they ask what was agreed. Use when they run a POC, change the client's codebase, prove it on their staging, go live, or need evals before a model acts. Use when they prep a…
pm-arch
Skill "pm-arch" from wei63w/pm-manager, covering user input, outline, done when and shared workflow (all /pm- commands).