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/lacs-project/sysknife/claude-mdgit clone --depth 1 https://github.com/lacs-project/sysknifeWrote 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/lacs-project/sysknife/claude-md)<a href="https://agentmods.dev/instructions/lacs-project/sysknife/claude-md"><img src="https://agentmods.dev/badge/instructions/lacs-project/sysknife/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 | $0.02204 | $0.02204 |
| Opus 5 | $0.01102 | $0.01102 |
| Sonnet 5 | $0.00441 | $0.00441 |
| Haiku 4.5 | $0.00220 | $0.00220 |
Grade A, and why
sysknife 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 3d 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 — 218 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SysKnife Operating Notes
This repository is for SysKnife, the Linux Agent Control Standard. Work here must preserve the trust boundary between the planner, the shell, and the privileged daemon.
Current Focus — Ubuntu; GUI Paused
GUI development is temporarily paused. Do not review, test, refactor, or
extend apps/sysknife-shell/** (the Tauri desktop app). It stays in the tree
and must keep building, so workspace-wide gates still cover it, but it is not
where effort goes. Merging a dependency bump that only touches its lockfile is
fine — that is maintenance, not development.
Analysis and development focus on Ubuntu, across its versions (22.04, 24.04, 26.04). Live-VM evidence, action coverage, and security review target the Debian-family path first.
Fedora is deprioritized, not dropped. The rpm-ostree action family, the
atomic story family, and the FEDORA_ONLY_ACTIONS safety fence all stay
intact and must keep passing; nothing here licenses deleting them.
Pre-Commit Gate
cargo nextest run --workspace --locked must pass with zero failures before
any commit. Fix every failing test — do not commit with known
pre-existing failures. If a test asserts the wrong value, fix the test
assertion to match the code (or fix the code if the test is right); do
not skip or ignore the test.
Repository Workflow
- Use isolated git worktrees for feature work.
- Prefer one branch per task or tightly related task batch.
- Keep branches small, reviewable, and focused on a single concern.
- Use the PR template for every pull request.
- Open PRs only against
main. - Request a code review before merge.
- Apply review fixes, commit them, and push the branch again.
- Merge only after the branch is reviewed and the checks pass.
- Never leave green PRs hanging. A PR with all required checks passing is ready to merge. Dependabot PRs included — once their CI is green, merge them the same day. Open PRs accumulate merge conflicts, blow up signal-to-noise, and leave security fixes effectively unshipped.
- Delete the remote branch after merge.
- Delete the local branch after merge.
- Delete the worktree directory after merge.
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.
- 3d ago First seen · 218 lines · 2,204 tokens per session scan A 0596eb803297
sysknife CLAUDE.md is an instructions file published in the GitHub repository lacs-project/sysknife (8 stars, last pushed 6d ago), licensed MIT. It adds 2,204 tokens to every session, about $0.0110 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 instructions, from other repositories
CORE CLAUDE.md
Instructions for DariuszNewecki/CORE, covering claude.md — core, what core is, and what you are, source layout, how to work in this repo and governed and prohibited surfaces.
orloj AGENTS.md
Instructions for OrlojHQ/orloj, covering orloj agent instructions, must-follow sync rules and working style.
orloj CLAUDE.md
Instructions for OrlojHQ/orloj, covering orloj claude instructions, critical repository rules and implementation notes.
agentfootprint AGENTS.md
Instructions for footprintjs/agentfootprint, covering agentfootprint — agent instructions (openai codex), core thesis, the mental model — three slots, six flavors, mock-first development (recommended workflow) and public api.
agentfootprint CLAUDE.md
Instructions for footprintjs/agentfootprint, covering agentfootprint — feature-work map, before you design it: it may already exist, module map, core state & flow and extension points.
nio CLAUDE.md
Instructions for core0-io/nio, covering nio, skill, project structure, build and release.