Borrowing it
Nothing to install: this file belongs to AleksandarBisevac/claude-plugins. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/AleksandarBisevac/claude-plugins/main/CLAUDE.mdgit clone --depth 1 https://github.com/AleksandarBisevac/claude-pluginsWrote 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/instructions/aleksandarbisevac/claude-plugins/claude-md)<a href="https://agentmods.dev/instructions/aleksandarbisevac/claude-plugins/claude-md"><img src="https://agentmods.dev/badge/instructions/aleksandarbisevac/claude-plugins/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/instructions/aleksandarbisevac/claude-plugins/claude-md"><img src="https://agentmods.dev/badge/instructions/aleksandarbisevac/claude-plugins/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 | $0.05745 | $0.05745 |
| Opus 5 | $0.02873 | $0.02873 |
| Sonnet 5 | $0.01149 | $0.01149 |
| Haiku 4.5 | $0.00575 | $0.00575 |
Grade A, and why
claude-plugins CLAUDE.md scanned grade A with 1 finding 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 yesterday.
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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
the Release is the page a reader lands on, and the README's `curl` pins make the tag a How it starts
The opening of the file, as written. The whole thing — 356 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Working on this repo
A Claude Code plugin marketplace (quality-gates → plugin audit). Python here is hooks and
CLI scripts, not a package: there is no [project] table, nothing is installed, nothing is
published. It dogfoods its own plugin, so its hooks fire on your edits.
Which tier the plan gate is in is not a property this file may assert (F57). The gate grades
itself on evidence — observe with no manifest, warn with a manifest but nothing running, deny once
a phase is in_progress — and this sentence used to say edits "run under" it, which reads as the
denying tier while only the weakest reading was true: the dogfood manifest's phases were all
finished when that was written, so the gate was advisory here and had been for releases. That is
exactly the kind of fact a document cannot keep. A document that names a gate owes the reader its
tier or should not name the gate, and the tier is computed rather than written down — so ask the
thing that computes it:
/audit:doctor # prints which tier is active and what put it there
The TDD reminder is unconditional and non-blocking, so it needs no tier.
CONTRIBUTING.md is the rulebook and PLUGIN-BUILD-GUIDE.md is the architecture. This file
states only what you must know before an edit; it deliberately restates no procedure, because
two copies of a procedure is one copy and one lie.
Hard rules
- Stdlib only in
plugins/audit/{hooks,scripts}/. A guard that needspip installis a guard that is off on most machines.py-launch.shstays POSIX-sh builtins only. - No
typing, nodataclasses, no annotations, no walrus, nofrom __future__. Not a style guide —_output.house_style_violations()reads the AST and fails the build. The 3.8 floor and hooks that must start fast on every tool call are the reason. - Python 3.8 floor, held by
vermin -t=3.8-in CI. Formatting is%-style throughout; the tree contains no f-strings. - Every
.pyunderhooks/andscripts/is scanned wherever it sits — CI's sweep and the lints in_output.pyand_deps.pyall walk recursively. The old rule saying files must stay one directory deep existed only because those scanners were flat, so a file in a subdirectory silently stopped being tested; that reason is gone. The one cost is that a.pybasename must be unique across the whole ofscripts/, sinceimportand_loaderboth resolve by basename —layer_violations()reports a collision by name.scripts/ui/still holds no.py. _output.pyis the anchor and never moves.SCRIPTS_DIR,PLUGIN_ROOT,HOOKS_DIR,TESTS_DIRandREPO_ROOTlive there and nowhere else;install_path()putsscripts/and every subdirectory of it holding a.pyonsys.path. The folders are labels, not namespaces — one flat name-space, every module reached by bare basename. No other.pyunderscripts/may read__file__outside the pinned preamble (depth_sensitive_paths()).- Fail-open for advisory paths, fail-loud for guards — the table is in
SECURITY.md. - Every claim in output carries the basis that makes it true, and when the basis is missing,
that is the thing to say. Never fall back to a default to fill the gap; a basis with no claim
is noise. See
CONTRIBUTING.mdfor the worked example (cost, and the five surfaces that render it). - Do not write a number into prose when something already prints it. This is the repo's
most frequent defect (F29, F39, F43 are one bug three times), and it is now a lint:
_output.prose_number_claims()over every.pythis repo keeps and_deps.doc_prose_numbers()over every.md— both sets derived off.gitignore, so a file added here is scanned by default and excluding one means a row in_output.PROSE_SCAN_EXEMPTwith a reason. They fail the build on a present-tense cardinality (its N cases), persistence (`NAME` stayed at N) or completeness (all N of them,all N … have) claim — and the number may be spelled as a word, which is F59:_numeral_span()reads both spellings, for every shape, from one fixed table. Three things stay legal on purpose: history (it stood at N that day), a number carrying the command that re-derives it — the basis may sit on the next line, because prose wraps — and the repair itself, which is to delete the number and keep the pointer.CONTRIBUTING.md's Writing a count that is allowed states those three affirmatively, with one example each; read it before writing a number rather than after a build refuses one. When a number really is informative, carry the basis; a basis makes a claim checkable, but only deleting the number stops it rotting. - Every command that mutates the manifest revalidates via
scripts/manifest/validate-manifest.py. COMPATIBILITY.mdis a contract, not a description. It promises that ameta.versionthe plugin accepts keeps being accepted and that a config key it reads keeps being read. So removing either, or changing which of two keys wins, is no longer a judgement call — it is a major release. Adding is always free. The document also names what is deliberately not promised; extend that list rather than quietly widening the promise.
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.
- yesterday Changed · +4 lines · +60 tokens per session a28f1689f2e0
- 5d ago Changed · +18 lines · +314 tokens per session 0793170e267e
- 9d ago First seen · 334 lines · 5,371 tokens per session scan A 585a87505624
claude-plugins CLAUDE.md is an instructions file published in the GitHub repository AleksandarBisevac/claude-plugins (4 stars, last pushed today), licensed MIT. It adds 5,745 tokens to every session, about $0.0287 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.