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-doc-sync-campaignnpx skills add BostonOrange/claude-code-framework --skill ccf-doc-sync-campaigngit clone --depth 1 https://github.com/BostonOrange/claude-code-frameworkWrote 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/bostonorange/claude-code-framework/ccf-doc-sync-campaign)<a href="https://agentmods.dev/skills/bostonorange/claude-code-framework/ccf-doc-sync-campaign"><img src="https://agentmods.dev/badge/skills/bostonorange/claude-code-framework/ccf-doc-sync-campaign.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 | $0.00157 | $0.04034 |
| Opus 5 | $0.00078 | $0.02017 |
| Sonnet 5 | $0.00031 | $0.00807 |
| Haiku 4.5 | $0.00016 | $0.00403 |
Grade A, and why
ccf-doc-sync-campaign 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 — 156 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Doc-Sync Campaign — Kill Count/Table Drift
Doc/count drift is this repo's hardest live problem: the same counts (27 skills, 39 agents, 11 commands, 23 rules, 7 hooks) are stated in ~10 files, and only some are test-guarded. The iron rule: NEVER hand-edit a count in isolation — counts change only together with the files they count, verified by tests. A change is not done until EVERY doc surface reflects it.
Usage
Load this skill when: you added/removed/renamed anything under skills/ or templates/agents|commands|rules|hooks/ (every such change moves a count on multiple surfaces); tests/check-consistency.sh or tests/check-agent-registry.sh fails; you spotted a stale number or table row in README.md, CLAUDE.md, AGENTS.md, or docs/; or you were asked to run the drift-fix campaign below.
Do NOT use it for: what the counted objects are (ccf-domain-reference); why the invariants exist (ccf-architecture-contract); commit/session-end gating (ccf-change-control); .claude/ vs templates/ intentional-difference mechanics (ccf-dogfood-and-drift); test internals (ccf-testing-and-qa).
The Doc-Surface Matrix
One row per surface. "Guarded" = a deterministic test fails if it drifts. Verified 2026-07-11.
| Surface | What it states | Guarded by |
|---|---|---|
| README.md counts | 27 workflow skills, 39 AI agents, 11 quick commands, 23 file-pattern rules, 7 lifecycle hooks | tests/check-consistency.sh (regex on phrases like "N workflow skills") |
| README.md agent table | one row per agent | check-consistency.sh (row count) + check-agent-registry.sh (name presence) |
| setup.sh summary block (lines ~1300–1304) | all five counts | check-consistency.sh |
| setup.ps1 summary block (lines ~1124–1128) | all five counts | UNGUARDED for counts — check-placeholders.sh enforces only placeholder parity, not summary numbers |
| config/agents.json | canonical agent registry: name, category, model, blurb, description | check-agent-registry.sh — description must be byte-identical to the agent file's frontmatter description |
| templates/CLAUDE.md.template | agent names, team table | names guarded (check-agent-registry.sh); team-size numbers (e.g. "All 15") and counts UNGUARDED |
| docs/teams.md | roster table + prose counts | names guarded; roster header + "pre-configured agents" prose guarded by check-consistency.sh since 2026-07-11 |
| docs/agents-commands-rules.md | agent/command/rule tables + prose | names guarded; prose counts UNGUARDED |
| docs/agent-patterns.md | prose agent count | "framework has N agents" guarded by check-consistency.sh since 2026-07-11 |
| AGENTS.md (Codex mirror of CLAUDE.md) | full file-tree counts + tables | four core counts guarded by check-consistency.sh since 2026-07-11 (first occurrence per phrase only — head -1); tables/team sizes UNGUARDED |
| CLAUDE.md (top-level, dogfood) | counts + agent/team tables | four core counts guarded by check-consistency.sh since 2026-07-11 (first occurrence only); tables/team sizes UNGUARDED |
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 · 156 lines · 157 tokens per session scan A 04c92cb18f73
ccf-doc-sync-campaign is a skill published in the GitHub repository BostonOrange/claude-code-framework (2 stars, last pushed 1mo ago), licensed MIT. It adds 157 tokens to every session and 4,034 once invoked, about $0.0008 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…