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-domain-referencenpx skills add BostonOrange/claude-code-framework --skill ccf-domain-referencegit 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 | $0.00150 | $0.03749 |
| Opus 5 | $0.00075 | $0.01875 |
| Sonnet 5 | $0.00030 | $0.00750 |
| Haiku 4.5 | $0.00015 | $0.00375 |
Grade B, and why
ccf-domain-reference scanned grade B 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 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.
Enumerates other installed skillsmediumAgent snooping
Other skills' SKILL.md files reveal prompts, capabilities and secrets that should be invisible to peers.
ls .claude/skills/ | grep -cv '^ccf-' # 2 dogfooded workflow skills (improve, team) Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
| `config/notifications.json` | Per-system webhook curl snippets (env var name, message field) | — | How it starts
The opening of the file, as written. The whole thing — 166 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CCF Domain Reference — Vocabulary, Object Model, Counts
Usage
Load this skill when you need to know what a thing is or how many exist in this repo: the seven content kinds, the placeholder registry, the CCF_* env interface, project types, or any config/*.json file. This is a lookup table, not a runbook.
Do NOT use this skill for:
- How to change things safely →
ccf-change-control - Which doc surface owns which count and fixing count drift →
ccf-doc-sync-campaign - Mirroring setup.sh into setup.ps1 →
ccf-parity-playbook - Running/installing the framework →
ccf-release-and-install - Why
.claude/differs fromtemplates/→ccf-dogfood-and-drift
The Seven Content Kinds
The framework ships seven kinds of content. Definitions apply to both the distributable copies (under skills/ and templates/) and the dogfooded subset (under .claude/).
| Kind | Location (distributable) | Format | Invoked as |
|---|---|---|---|
| Skill | skills/<name>/SKILL.md |
YAML frontmatter name + description, then markdown instructions (numbered phases for workflows) |
/name slash command in a session |
| Agent | templates/agents/<name>.md |
Frontmatter name, description, tools, model (opus by default) |
Spawned as a subagent, directly or via /team |
| Command | templates/commands/<name>.md |
Frontmatter name, description, allowed-tools; single-purpose (one action, one output) |
/name, but simpler than a skill — no phases |
| Rule | templates/rules/<name>.md |
Frontmatter id (kebab-case, stable forever — the citation key reviewer agents use) + patterns array of globs |
Auto-applied guardrail when edited files match patterns; cited by id in review findings |
| Hook | templates/hooks/<name>.sh |
Bash, #!/bin/bash; exit 0 = success, 1 = soft block (prompt user), 2 = hard block |
Wired in settings.local.json lifecycle events (PreToolUse, PostToolUse, SessionStart, SessionEnd) or .git/hooks/ |
| Team | Defined in the team skill |
Pre-configured agent group (review, architecture, release, quality, documentation, design, full, custom) | /team <name> — compositions table lives in CLAUDE.md "Agent Teams" |
| Global skill | global-skills/<name>/ |
Same format as a skill | Installed account-wide into ~/.claude/skills/ by install-global-skill.sh / .ps1; NOT copied into target repos, NOT counted in the "27 workflow skills". Only one exists: install-framework |
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 · 166 lines · 0 tokens per session scan B ff5a54e2dac6
ccf-domain-reference is a skill published in the GitHub repository BostonOrange/claude-code-framework (2 stars, last pushed 1mo ago), licensed MIT. It adds 150 tokens to every session and 3,749 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it B with 2 findings (enumerates other installed skills, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
mcporter
List, auth, and call MCP servers/tools from the terminal.
agent-messaging
Send and receive cryptographically signed messages between AI agents using the Agent Messaging Protocol (AMP). Use when the user asks to "send a message to an agent", "check agent inbox", "message another agent", "reply to a message", "notify an agent", or any inter-agent communication task.
📝 任务完成后归档
重要提醒: 每次完成复杂调试或开发任务后，主动执行此流程！ 将学到的经验归档为 skill，供以后参考。不要等用户提醒。.
oracle
Best practices for using the oracle CLI (prompt + file bundling, engines, sessions, and file attachment patterns).
agent-mode
Unified tool for managing agent LLM modes (add, remove, update, list, switch).
agento11y-prod-setup
Sets up production evaluation and guardrails for a DEPLOYED AI agent in Grafana Agent Observability, grounded in the agent's own code and its real ingested traffic. The judgment layer on top of the agento11y skill: it reads the agent's source (system prompt, tools, entrypoint) AND samples its live traffic via gcx…