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-release-and-installnpx skills add BostonOrange/claude-code-framework --skill ccf-release-and-installgit 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-release-and-install)<a href="https://agentmods.dev/skills/bostonorange/claude-code-framework/ccf-release-and-install"><img src="https://agentmods.dev/badge/skills/bostonorange/claude-code-framework/ccf-release-and-install.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 | $0.00127 | $0.04143 |
| Opus 5 | $0.00063 | $0.02072 |
| Sonnet 5 | $0.00025 | $0.00829 |
| Haiku 4.5 | $0.00013 | $0.00414 |
Grade D, and why
ccf-release-and-install scanned grade D with 2 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
grep -R "{{[A-Z_][A-Z_]*}}" CLAUDE.md .claude 2>/dev/null | grep -v ".claude/state" | grep -v ".claude/skills/improve/SKILL.md" Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
3. **Global skill** — `bash install-global-skill.sh` (from a framework clone) copies `global-skills/install-framework/` into `~/.claude/skills/install-framework` (rm -rf's any existing copy first). Then `/install-framewo How it starts
The opening of the file, as written. The whole thing — 162 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Release and Install: How the Framework Gets Into (and Out of) a Target Repo
There is no package registry, build artifact, or version pinning — "releasing" the framework means running setup.sh (bash, requires python3) or setup.ps1 (PowerShell, no python dependency) from inside a target repo; the installer reads templates from the framework clone and substitutes {{PLACEHOLDER}} values from config/*.json. Never run the installers inside the framework repo itself (CLAUDE.md: "Do not run setup.sh here"); test in a throwaway dir per CLAUDE.md's "Testing Changes".
Usage
Load this skill to run or debug an installation: choosing an install path, the exact flag/CCF_* interface, what files the installers write, uninstalling, or the Windows parity traps that affect operators.
Do NOT load it for:
- Editing setup.sh/setup.ps1 → ccf-parity-playbook (mirror discipline, sed/python3/PS traps)
- Placeholder/vocabulary/config-catalog questions → ccf-domain-reference
- The setup smoke test and merge gates → ccf-testing-and-qa and ccf-change-control
- Why this repo's own
.claude/differs fromtemplates/→ ccf-dogfood-and-drift
Process: standard install (non-interactive, recommended for agent sessions)
$FRAMEWORK_CLONE below = path to a clone of claude-code-framework.
- Preflight (in the target repo):
git rev-parse --git-dir(should be a git repo; not fatal but branch/pre-commit steps are skipped otherwise) and, on the bash path,command -v python3— setup.sh exits 1 immediately without it. - Preview without prompts — combine both flags;
--dry-runalone still runs the interactive prompts:
Bash printsCCF_PROJECT_TYPE=nodejs bash "$FRAMEWORK_CLONE/setup.sh" --non-interactive --dry-run[DRY-RUN]lines plus a config summary and exits 0 before any write. - Install:
CCF_PROJECT_TYPE=nodejs CCF_TRACKER=github CCF_CICD=github-actions \ CCF_BASE_BRANCH=main CCF_PROJECT_SHORT_NAME=myapp CCF_DESIGN_SYSTEM=none \ bash "$FRAMEWORK_CLONE/setup.sh" --non-interactive - Verify — no unreplaced placeholders may remain:
Any output = failed install; do not report success (this is the same checkgrep -R "{{[A-Z_][A-Z_]*}}" CLAUDE.md .claude 2>/dev/null | grep -v ".claude/state" | grep -v ".claude/skills/improve/SKILL.md"/install-frameworkmandates). - Rollback if needed — see Rollback below.
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 · 162 lines · 127 tokens per session scan D 31c0c9916680
ccf-release-and-install is a skill published in the GitHub repository BostonOrange/claude-code-framework (2 stars, last pushed 1mo ago), licensed MIT. It adds 127 tokens to every session and 4,143 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it D with 2 findings (reads agent configuration directories, recursive force delete). 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…