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/bostonorange/claude-code-framework/ccf-change-controlnpx skills add BostonOrange/claude-code-framework --skill ccf-change-controlgit clone --depth 1 https://github.com/BostonOrange/claude-code-frameworkWhat 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 | $0.00114 | $0.03043 |
| Opus 5 | $0.00057 | $0.01522 |
| Sonnet 5 | $0.00023 | $0.00609 |
| Haiku 4.5 | $0.00011 | $0.00304 |
Grade B, and why
ccf-change-control scanned grade B 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 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
- Rule-id stability rule: `grep -n 'stable forever' .claude/rules/templates.md` How it starts
The opening of the file, as written. The whole thing — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CCF Change Control
How a change to this framework is classified, gated, reviewed, and landed. The core model: deterministic tests are the hard gate; agents are advisory layers on top of it. No agent opinion, review, or skill instruction may route around a failing tests/run-all.sh.
Usage
Load this skill when you are about to change framework files and need to know what must happen before the change counts as done — or when you see a failing check and need to know whether to fix the change or the check.
Do NOT use this skill for:
- WHICH count/table lives in WHICH file — that matrix is owned by ccf-doc-sync-campaign
- HOW to mirror setup.sh into setup.ps1 — ccf-parity-playbook
- Internals of each
tests/check-*.shscript — ccf-testing-and-qa - Mechanics of
.claude/vstemplates/and the drift allowlist format — ccf-dogfood-and-drift
Process
1. Classify the change
| Class | Examples | Minimum gate | Extra obligations |
|---|---|---|---|
| doc-only | README wording, docs/ guides | bash tests/run-all.sh (counts/tables are still parsed) |
None if no counts touched |
| template-content | new/edited file in templates/agents|commands|rules|hooks/, skills/ |
full suite; check-templates.sh, check-placeholders.sh, check-consistency.sh, check-agent-registry.sh, check-dogfood-drift.sh all bite |
Update every doc surface + config/agents.json for agents (see ccf-doc-sync-campaign); sync or allowlist the .claude/ twin |
| setup-script | setup.sh / setup.ps1 |
full suite incl. check-setup-smoke.sh; PowerShell smoke (see phase 3 warning) |
Mirror in the other script in the SAME change (.claude/rules/setup-scripts.md) |
| test | tests/check-*.sh, tests/check-setup-smoke.ps1 |
full suite; new check-*.sh files are auto-discovered by run-all.sh (find pattern) |
State what the test newly gates in the commit message |
| config-schema | config/*.json |
full suite; check-agent-registry.sh locksteps config/agents.json with templates/agents/*.md, README.md, templates/CLAUDE.md.template, docs/teams.md, docs/agents-commands-rules.md |
Treat keys as an interface consumed by setup scripts |
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 · 127 lines · 114 tokens per session scan B 0e7a3294b37e
ccf-change-control is a skill published in the GitHub repository BostonOrange/claude-code-framework (2 stars, last pushed 1mo ago), licensed MIT. It adds 114 tokens to every session and 3,043 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). 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…