Borrowing it
Nothing to install: this file belongs to BostonOrange/claude-code-framework. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/BostonOrange/claude-code-framework/main/.claude/skills/ccf-dogfood-and-drift/SKILL.mdgit 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-dogfood-and-drift)<a href="https://agentmods.dev/skills/bostonorange/claude-code-framework/ccf-dogfood-and-drift"><img src="https://agentmods.dev/badge/skills/bostonorange/claude-code-framework/ccf-dogfood-and-drift/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/bostonorange/claude-code-framework/ccf-dogfood-and-drift"><img src="https://agentmods.dev/badge/skills/bostonorange/claude-code-framework/ccf-dogfood-and-drift.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00138 | $0.03545 |
| Opus 5 | $0.00069 | $0.01773 |
| Sonnet 5 | $0.00028 | $0.00709 |
| Haiku 4.5 | $0.00014 | $0.00354 |
Grade A, and why
ccf-dogfood-and-drift 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 9d 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 — 170 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Dogfood Model and Drift Policing
Dogfooding here means: this repo runs a copy of its own product under .claude/. But .claude/ is not a setup.sh install — it is a hand-curated subset, and every byte of divergence between .claude/ and the distributable sources is policed by an explicit allowlist (config/dogfood-drift-allowlist.txt) enforced by tests/check-dogfood-drift.sh.
Usage
Load this skill when:
tests/check-dogfood-drift.shfails (unexpected or stale entries).- You are adding, modifying, or removing anything under
.claude/agents/,.claude/hooks/,.claude/skills/,.claude/statusline/, or.claude/settings.local.json. - You are adding a template skill/agent/hook that will NOT be dogfooded (that also changes the drift surface — see Edge Cases).
- You need to decide: allowlist a divergence, or sync it back to the template?
Do NOT use this skill for:
- The full test-suite anatomy or "am I done?" gating — see ccf-testing-and-qa.
- Doc counts/tables (README, CLAUDE.md, AGENTS.md) — see ccf-doc-sync-campaign.
- Whether a change may merge at all, commit conventions — see ccf-change-control.
- Why the repo separates
templates/vsskills/vsglobal-skills/— see ccf-architecture-contract.
Process: touching anything the drift check compares
Phase 1 — Classify your change
| You are... | Go to |
|---|---|
Adding a repo-local file under .claude/ (skill, agent) |
Phase 2 |
| Modifying a dogfooded copy of a template file | Phase 3 |
| Removing anything (either side) | Phase 4 |
| Adding a template-side skill/agent/hook that is NOT dogfooded | Edge Cases table |
Phase 2 — Add a repo-local skill or agent
mkdir -p .claude/skills/<name>
# write .claude/skills/<name>/SKILL.md
printf 'Only in .claude/skills: %s\n' '<name>' >> config/dogfood-drift-allowlist.txt
bash tests/check-dogfood-drift.sh
For a repo-only agent the line is Only in .claude/agents: <name>.md (note .md — agents are compared per-file, skills per-directory). The script sorts everything, so line position doesn't matter for correctness — but group lines under the file's existing comment headers for humans.
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.
- 9d ago First seen · 170 lines · 138 tokens per session scan A cbdfef5d8201
ccf-dogfood-and-drift is a skill published in the GitHub repository BostonOrange/claude-code-framework (2 stars, last pushed 1mo ago), licensed MIT. It adds 138 tokens to every session and 3,545 once invoked, about $0.0007 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.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…