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 skills/negai-ai/agentclaw/coding_skillnpx skills add Negai-ai/AgentClaw --skill coding_skillgit clone --depth 1 https://github.com/Negai-ai/AgentClawWhat 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 | $0.00052 | $0.04550 |
| Opus 5 | $0.00026 | $0.02275 |
| Sonnet 5 | $0.00010 | $0.00910 |
| Haiku 4.5 | $0.00005 | $0.00455 |
Grade A, and why
coding_skill 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 — 502 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Coding Skill (Primary Playbook)
This SKILL.md is the default guide for common coding tasks.
Focus on reliable tool usage and verifiable code changes.
Load references/* only when needed.
1) Scope and Boundary
- This skill covers generic coding work: discover, read, edit, refactor, and validate code.
- This skill is tool-centric. Keep guidance about product/domain-specific implementation out of the main flow.
- All coding-tool paths are resolved under
project_dir. Paths outsideproject_dirare invalid. - Use minimal edits first; escalate to broad rewrites only when partial edits are unstable.
- Do not introduce hardcoded secrets, machine-specific absolute paths, or environment-specific install commands in generated code.
2) Zero-Context Execution Flow (Default)
When repository context is limited, use this fixed sequence:
search_codeto locate files/snippets.- Run quick environment preflight for path/tool consistency:
- confirm
project_dir-relative target paths - avoid bare
pip; prefer interpreter-scoped install commands when needed
- confirm
read_codeto load exact edit context.- Apply smallest safe edit (
replace_in_fileorupdate_code). - For Python edits:
- If you used
write_code: syntax is already validated (pre-write check). Do NOT callsyntax_checkin the same tool call — the file won't exist yet when parallel tools run. Only usesyntax_checkseparately forreplace_in_file/update_codeedits. python -m py_compile <changed_file>.py(optional, for import-level validation; on Windows you may also usepy -3 -m py_compile)
- If you used
- If syntax fails, patch the failing region with local edits first (
replace_in_file/update_code), then re-run checks. - Re-read changed region (
read_code) when ambiguity/count errors occurred. - Report changed files, validations, and unresolved risks.
Prefer not to skip to later steps when an earlier step fails.
3) Tool Contract (Default)
3.1 search_code
Purpose: text/regex discovery in project files. Returns file:line:col: matched_text for each match.
What ships with it
1 file 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.
- 3d ago First seen · 502 lines · 52 tokens per session scan A 1fa0ba3b0b57
coding_skill is a skill published in the GitHub repository Negai-ai/AgentClaw (340 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 52 tokens to every session and 4,550 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…