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/ssbun/csl-agent-kit/agent-rulesnpx skills add SSBun/csl-agent-kit --skill agent-rulesgit clone --depth 1 https://github.com/SSBun/csl-agent-kitWhat 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 | $0.00057 | $0.00550 |
| Opus 5 | $0.00028 | $0.00275 |
| Sonnet 5 | $0.00011 | $0.00110 |
| Haiku 4.5 | $0.00006 | $0.00055 |
Grade A, and why
agent-rules 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 2d 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 — 43 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Rules
Manage unconditional Agent behavior rules loaded at session start.
Storage and loading
| Scope | Path | Purpose |
|---|---|---|
| Built-in | skills/meta/agent-rules/agent-rules.md |
Read-only defaults distributed with CSL Agent Kit. |
| User | $CSL_AGENT_KIT_HOME/agent-rules.md (default ~/.csl-agent-kit/agent-rules.md) |
Writable rules that apply across projects. |
| Project | <workspace>/.agents/agent-rules.md |
Writable rules for one workspace. |
The built-in Agent Hooks rule inner:agent-rules loads these files in built-in, user, then project order. It injects all non-empty content under one ## Agent Rules heading without modifying any source.
File format
Every scope uses one agent-rules.md Markdown list. Each top-level - item is one short imperative rule. Do not add YAML frontmatter.
- Confirm before destructive Git commands such as force-push or reset --hard.
Workflow
- Determine the scope. Use user scope by default for cross-project preferences and project scope for repository-specific behavior. Modify built-in rules only when the user explicitly requests a package change.
- Resolve the scope's single
agent-rules.md. Honor$CSL_AGENT_KIT_HOMEfor user scope and the active workspace for project scope. - Add, edit, remove, or list rules. Merge or skip duplicates and preserve unrelated rules.
- Write user and project files atomically. Keep the built-in file version-controlled with the package.
- Report the changed scope and path. Changes take effect on the next session start; the current session is not retroactively updated.
- Verify
inner:agent-ruleswithnode skills/meta/agent-hooks/scripts/agent-hooks.js show inner:agent-rules --host pi, then verify built-in, user, and project combinations and their merge order.
Boundaries
- Rules are unconditional. Prefer observable, checkable directives over vague preferences.
AGENTS.mdandCLAUDE.mdremain host-owned instruction files outside this system.- Conditional matching, scripts, notifications, and runtime guards belong in Agent Hooks.
- Keep rules short. Graduate longer procedures into Agent SOPs.
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.
- 2d ago First seen · 43 lines · 57 tokens per session scan A 55570bf31967
agent-rules is a skill published in the GitHub repository SSBun/csl-agent-kit (10 stars, last pushed 4d ago), licensed MIT. It adds 57 tokens to every session and 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 2026-08-31.
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…