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 DmitriyYukhanov/claude-plugins/plugin install claude-md-slimWrote 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/dmitriyyukhanov/claude-plugins/slim-claude-md)<a href="https://agentmods.dev/skills/dmitriyyukhanov/claude-plugins/slim-claude-md"><img src="https://agentmods.dev/badge/skills/dmitriyyukhanov/claude-plugins/slim-claude-md/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/dmitriyyukhanov/claude-plugins/slim-claude-md"><img src="https://agentmods.dev/badge/skills/dmitriyyukhanov/claude-plugins/slim-claude-md.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 | $0.00064 | $0.01571 |
| Opus 5 | $0.00032 | $0.00785 |
| Sonnet 5 | $0.00013 | $0.00314 |
| Haiku 4.5 | $0.00006 | $0.00157 |
Grade A, and why
slim-claude-md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Slim a CLAUDE.md
CLAUDE.md loads in full on every session. Past roughly 200 lines it costs context on every request
and reduces adherence, so instructions get ignored precisely because there are too many of them.
This moves subsystem detail into .claude/rules/ files that load only when the matching files are
opened, and proves the move lost nothing.
Scope: restructuring an existing file. Writing a CLAUDE.md from scratch is /init's job; auditing
content quality against templates is what claude-md-management's claude-md-improver does.
Mechanics (load order, paths: syntax, the @import trap, /doctor, hierarchy) live in
references/mechanics.md. Read the section you need when you need it.
Phase 1 — Measure
python "${CLAUDE_PLUGIN_ROOT}/skills/slim-claude-md/scripts/audit_claude_md.py" CLAUDE.md
Reports loaded size (HTML comments excluded, since they are stripped before loading), ranks sections by size, marks the set whose removal gets you under budget, and flags derivable content plus staleness hints. Exit 1 means over budget.
Run it on every CLAUDE.md in the repo, not just the root one: find . -name CLAUDE.md -not -path "*/node_modules/*".
If the file is within budget, stop and say so. Do not restructure a file that is already fine.
Phase 2 — Decide what moves
For each section, apply the documented test: "Would removing this cause Claude to make mistakes? If not, cut it." Then sort what remains into three piles.
Stays in CLAUDE.md — needed in every session regardless of what you touch:
- Build/test commands that can't be guessed
- Safety rules ("never run X", "never commit Y") — these must never be behind a path scope
- Conventions that apply repo-wide
- Gotchas that bite before you open any particular file
Moves to a paths:-scoped rule — only matters while editing one subsystem:
- Per-feature implementation narratives
- Deep rationale for one module's design
- Anything whose first sentence is effectively "when working on X…"
What ships with it
3 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.
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 · 146 lines · 64 tokens per session scan A 127f7415c8f6
slim-claude-md is a skill published in the GitHub repository DmitriyYukhanov/claude-plugins (7 stars, last pushed 2d ago), licensed MIT. It adds 64 tokens to every session and 1,571 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 skills, from other repositories
code-standards
Prabhdeep (Sonu) Singh's personal coding standards — the house rules and quality bar for how code gets written. INVOKE before writing, generating, refactoring, or reviewing ANY code in ANY language — schemas, endpoints, queries, logging, validation, error handling — even when nobody says "standards" or "style".…
self-review
Surface the riskiest parts of the current diff so a reviewer knows where to look hardest — one inline pass on small diffs, one cold read on a cheaper model tier with in-session synthesis on substantial ones. INVOKE PROACTIVELY whenever a change is finished and about to be handed off, reviewed, or shipped. It points…
ticket-lifecycle
The ticket-as-control-plane rulebook — the single home for the tracker-operations contract, tracker resolution, the type/priority taxonomy, human-only trigger authorization, derived status, and trust boundaries. INVOKE when reading or writing tickets in a queue-driven flow, resolving a repo's tracker, or deciding…
design-tree
Make design decisions as an explicit branching tree — genuine alternatives, decisive rationale, rejected branches preserved. INVOKE PROACTIVELY when planning or designing any implementation approach, or choosing between architectures, libraries, or data models — especially in plan mode. Skip trivial or forced changes…
pr-conventions
Author PR descriptions from the right per-change-type template (the repo's own PULLREQUESTTEMPLATE wins), embed issue-tracker links, keep the description current as fixes land, and reply to human and bot review threads. INVOKE when opening or updating a PR or responding to reviewer comments — inside /sonu:ship or…
infra-standards
Infrastructure, container, and CI/CD discipline — IaC, Dockerfiles and compose files, CI pipelines, platform deploy config, env/secrets handling. INVOKE PROACTIVELY when creating or editing any such file (.tf, .bicep, Dockerfile, docker-compose, .github/workflows/, vercel.json) — even when nobody says "infra". Not for…