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-sopsnpx skills add SSBun/csl-agent-kit --skill agent-sopsgit clone --depth 1 https://github.com/SSBun/csl-agent-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/skills/ssbun/csl-agent-kit/agent-sops)<a href="https://agentmods.dev/skills/ssbun/csl-agent-kit/agent-sops"><img src="https://agentmods.dev/badge/skills/ssbun/csl-agent-kit/agent-sops.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 | $0.00067 | $0.01731 |
| Opus 5 | $0.00034 | $0.00865 |
| Sonnet 5 | $0.00013 | $0.00346 |
| Haiku 4.5 | $0.00007 | $0.00173 |
Grade A, and why
agent-sops 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 4d 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 — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent SOPs
Manage Standard Operating Procedure (SOP) files. SOPs are Agent behavior rules loaded on demand: when a task matches an SOP's when_to_use or name, read the complete SOP before following its process or rules.
Storage and precedence
| Scope | Path | Purpose |
|---|---|---|
| Built-in | skills/meta/agent-sops/sops/*.md |
SOPs distributed with the package. |
| User | ~/.csl-agent-kit/sops/*.md |
User-created SOPs that apply across projects. |
| Project | <workspace>/.agents/sops/*.md |
Version-controlled SOPs specific to the current workspace. |
For the same frontmatter name, precedence is project, then user, then built-in. Only the highest-precedence SOP is listed or routed.
SOP file format
Every SOP must begin with YAML frontmatter containing at least:
---
name: deploy-production
description: Deploy the production service safely.
when_to_use: Use when deploying the production service or investigating production deploy failures.
---
Use kebab-case for name. All frontmatter values must be English. Keep description brief. when_to_use must state when the SOP applies; it is the primary routing and summary field.
Optional fields:
version: 1.0
update_date: 2026-07-08
do_not_use_when:
- Use another SOP when uploading releases or publishing remote artifacts.
globs:
- "**/*.swift"
alwaysApply: false
Use do_not_use_when to prevent false positives. When a task matches both when_to_use and do_not_use_when, do not apply the SOP unless the user explicitly selects it.
Routing keywords
Prompt-time candidate matching scores keywords derived automatically from name, when_to_use, and globs (penalized by do_not_use_when); there is no separate keyword field. When generating or updating any SOP, make its routing fields matchable:
- Put concrete, distinctive terms in
nameandwhen_to_use: product or component names (e.g.Kanshan), specific techniques or formats (e.g.green-screen,Glyph JSON,DMG,Sparkle appcast), and stable tool or platform names. - Prefer terms a user would literally type when requesting the task; an exact
namehit scores highest, hyphen-separated name words also match. - Do not rely on generic words (
use,when,project,file,build,用于); they are stopwords or weak signals and are filtered or scored low. - Use
do_not_use_whenphrases that literally echo the adjacent SOP's distinctive terms, so the penalty fires on overlapping requests. - Keep
when_to_useone sentence; list the distinctive terms naturally instead of stuffing a keyword list.
What ships with it
21 files 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.
- references/code-style/swift-style.md 4.1 KB
- references/macos-build-run-debug/project-discovery-and-run-loop.md 5.5 KB
- references/macos-build-run-debug/swiftpm-gui-app-bundle.md 4.6 KB
- references/macos-build-run-debug/test-triage.md 3.5 KB
- references/macos-packaging-notarization/distribution-and-notarization.md 5.4 KB
- references/macos-signing-entitlements/diagnosis-and-entitlements.md 5.0 KB
- references/macos-swiftui-appkit/appkit-interop.md 5.4 KB
- references/macos-swiftui-appkit/scene-architecture.md 6.7 KB
- references/macos-swiftui-appkit/windowing-and-visuals.md 5.3 KB
- references/macos-unified-logging/logger-design-and-verification.md 4.4 KB
- references/process-sop-example.md 2.6 KB
- references/rule-sop-example.md 3.0 KB
- scripts/sop-candidates.js 5.3 KB runs code
- scripts/sop-summaries.sh 2.6 KB runs code
- sops/code-style.md 3.8 KB
- sops/macos-build-run-debug.md 8.9 KB
- sops/macos-packaging-notarization.md 8.7 KB
- sops/macos-signing-entitlements.md 8.4 KB
- sops/macos-swiftui-appkit.md 9.5 KB
- sops/macos-unified-logging.md 7.9 KB
- sops/swift-api-design.md 11 KB
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.
- 4d ago First seen · 138 lines · 67 tokens per session scan A 2f81fef7fc2d
agent-sops is a skill published in the GitHub repository SSBun/csl-agent-kit (10 stars, last pushed 2d ago), licensed MIT. It adds 67 tokens to every session and 1,731 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…