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 instructions/sharrmavishal/operating-kit/claude-mdgit clone --depth 1 https://github.com/Sharrmavishal/operating-kitWrote 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/sharrmavishal/operating-kit/claude-md)<a href="https://agentmods.dev/instructions/sharrmavishal/operating-kit/claude-md"><img src="https://agentmods.dev/badge/instructions/sharrmavishal/operating-kit/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 | $0.01086 | $0.01086 |
| Opus 5 | $0.00543 | $0.00543 |
| Sonnet 5 | $0.00217 | $0.00217 |
| Haiku 4.5 | $0.00109 | $0.00109 |
Grade A, and why
operating-kit 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 5d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl/query/grep returning a count before being called done. How it starts
The opening of the file, as written. The whole thing — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md: {{PROJECT_NAME}} Project Context
Read before every task. Operating method (how I work + how I think) is in
docs/claude/operating-principles.md. That file is stable across projects; this file
holds this project's specifics and grows over time.
What is {{PROJECT_NAME}}
{{One-paragraph description: what it does, who it's for, current phase/state. Replace this whole block.}}
Live state: {{prod URLs / environments / current milestone}}.
Tech stack
{{Languages, frameworks, DB, infra, key services. Note where secrets live and that they are never committed. Note any non-obvious build/deploy step (e.g. "run the build locally before pushing, since CI lint blocks deploys").}}
Operating mode (pointer)
Builder + strategic-vetting partner. Full rules in docs/claude/operating-principles.md.
The load-bearing gates, inline so they're never missed:
- Permission discipline. Read-only/diagnostic runs proceed freely. Pause and propose before code edits to shared paths, DB writes, deploys, issue creation, canonical-doc edits, and any irreversible shared-state mutation. Pre-authorized sequences ("ship it", an explicit ordered plan) proceed.
- Production-mutation pre-flight (hard gate). Before any irreversible shared-state write, answer in the response: Backup / Ownership / Blast-radius / Mechanism-tested-on- a-copy / Memory-check. (operating-principles A3.)
- Scratch-test destructive ops on a copy and show the diff before prod. (A4.)
- Make safety mechanical: encode gates in code, don't rely on remembering them. (A5.)
- Milestone gate. Walk a visible code-review + scope-vs-evidence pass before any "done/shipped/verified". (A6.)
- Verify-don't-infer. An output is not a finding until you've checked what produced it. (A7.)
- Code-change discipline. Before any non-trivial edit, follow
docs/claude/vigilance-protocol.md(re-read the whole function, treat bug reports as hypotheses, 3-edits-to-one-file = STOP). Driving a second model? Usedocs/claude/multi-model-collaboration.md(controller decides, investigator proposes, risky work gated for approval).
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.
- 5d ago First seen · 104 lines · 1,086 tokens per session scan A 615c9a261821
operating-kit CLAUDE.md is an instructions file published in the GitHub repository Sharrmavishal/operating-kit (2 stars, last pushed 1mo ago), licensed MIT. It adds 1,086 tokens to every session, about $0.0054 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 2026-08-30.
Other instructions, from other repositories
EverOS CLAUDE.md
Claude Code instructions for EverMind-AI/EverOS, covering everos — md-first memory extraction framework, quick commands, architecture, engineering practices and branch strategy.
connectonion AGENTS.md
AGENTS.md instructions for openonion/connectonion, covering agents.md, project overview, architecture, core components and key design patterns.
llm-wiki CLAUDE.md
Instructions for nvk/llm-wiki, covering llm-wiki development guide, testing, github auth and transport, structural tests (always run — no llm, instant) and behavioral evals (run when changing command logic).
OpenContracts CLAUDE.md
Claude Code instructions for Open-Source-Legal/OpenContracts, covering claude.md, project overview, baseline commit rules, essential commands and backend (django).
disp8ch AGENTS.md
AGENTS.md instructions for aaronnat23/disp8ch, covering agents, repo instructions and session startup.
mda CLAUDE.md
Instructions for sno-ai/mda, covering claude.md — sno-ai/mda, release process for @markdown-ai/cli, to cut a release (any 1.1.x, 1.2.0, 2.0.0 — same flow), release notes — non-negotiable and what's new.