Borrowing it
Nothing to install: this file belongs to fledgeling-co/fledgeling-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/fledgeling-co/fledgeling-plugins/main/CLAUDE.mdgit clone --depth 1 https://github.com/fledgeling-co/fledgeling-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/fledgeling-co/fledgeling-plugins/claude-md)<a href="https://agentmods.dev/instructions/fledgeling-co/fledgeling-plugins/claude-md"><img src="https://agentmods.dev/badge/instructions/fledgeling-co/fledgeling-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/fledgeling-co/fledgeling-plugins/claude-md"><img src="https://agentmods.dev/badge/instructions/fledgeling-co/fledgeling-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 | $0.03039 | $0.03039 |
| Opus 5.5 | $0.01216 | $0.01216 |
| Sonnet 5.5 | $0.00608 | $0.00608 |
| Haiku 4.5 | $0.00304 | $0.00304 |
Grade A, and why
fledgeling-plugins 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 1mo 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 — 224 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
Guidance for Claude Code when working in this repository.
Writing skill instructions and runner briefs
Write plugin skill referrals as exact plugin:skill identifiers in instructions,
prose and generated prompts: ship-feature:ship-feature, shipyard:triage,
test-campaign:test-campaign. Resolve them against the marketplace and skill
directories, then check the receiving runtime exposes them. A reference existing
in this repository does not prove it is installed or loaded in a runner. Inspect
the actual tool result; an unknown skill is a failed dependency, not a completed
phase. Discover a supported replacement or report the missing dependency.
Keep plugin install names, filesystem paths and frontmatter name values in
their own formats. Built-in, project and personal skills may legitimately have
bare runtime names; use the name the runtime advertises. Do not invent a
marketplace prefix. Historical changelogs, research and eval outputs preserve
the names that were used at the time.
The owner's preferred workflow is Opus 5 for intake, triage and planning, Gemini 3.8 for implementation after the plan, and GPT-6 for orchestration. Respect an explicit task-specific model choice first. These are role preferences, not API selectors or universal capability rankings: discover supported runtime selectors and verify the actual route, especially through Relay. An older model's benchmark or Gemini adapter does not establish a newer model's limitations.
Each handoff names its task, input artifact paths, scope, writable paths, available tools/skills, required outputs, acceptance evidence and stopping condition. Parallelize independent work with distinct ownership; serialize dependent phases and shared writes. Follow concrete project acceptance gates once, and repeat only after a relevant change, failure or unresolved finding. Remove generic repeated self-check instructions from Opus briefs without removing tests, visual judgments, independent acceptance or evidence the user requested.
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.
- 1mo ago Changed · +2 lines · +68 tokens per session ee35bcd847e9
- 1mo ago Changed · +41 lines · +547 tokens per session 1d2540265664
- 1mo ago First seen · 181 lines · 2,424 tokens per session scan A bfc7a19d9b32
fledgeling-plugins CLAUDE.md is an instructions file published in the GitHub repository fledgeling-co/fledgeling-plugins (2 stars, last pushed 2d ago), licensed MIT. It adds 3,039 tokens to every session, about $0.0122 per session on Opus 5.5. 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 instructions, from other repositories
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).
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
vscode model-prompts.instructions.md
Model-specific prompt authoring and registry guidelines.