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 instructions/dynamitecircle/dc/claude-mdgit clone --depth 1 https://github.com/dynamitecircle/dcWhat 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 | $0.02961 | $0.02961 |
| Opus 5 | $0.01481 | $0.01481 |
| Sonnet 5 | $0.00592 | $0.00592 |
| Haiku 4.5 | $0.00296 | $0.00296 |
Grade C, and why
dc CLAUDE.md scanned grade C with 3 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
This writes `py/.env.dc` (chmod 600). The file is gitignored. Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
**Pre-approval out of the box:** `.claude/settings.json`, `.codex/config.toml`, and `.gemini/settings.json` all auto-approve the `dc` MCP server's tools so users don't get a per-call approval prompt. Anyone uncomfortable Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- A small embedded mini-runtime — `Runtime` base class, `@skill_command` decorator, `ArgHelpers` (flag parsing, cursor pagination, envelopes), `HttpClient` (urllib-based) How it starts
The opening of the file, as written. The whole thing — 234 lines — stays where its author put it; the contents beside it link to each section on GitHub.
DC Official — AI Tool Guide
This repo ships official clients for the public DC Member API (https://api.dynamitecircle.com).
py/— self-contained, single-file Python client. CLI + Python library + Agent Skill + MCP server.ts/— TypeScript npm library, published as@dynamitecircle/dc. No CLI and no MCP server.contracts/— pinned OpenAPI snapshot + operation map used to validate Python and TypeScript parity.
At a glance
- One file:
py/dc.py - Three modes: CLI, Python import, MCP server (
--mcpflag) - Stdlib only for CLI/import. The
mcppackage is lazy-imported — only required for--mcpmode - Full coverage — every public Member API endpoint is wrapped (run
helpfor the live list) - Pinned contract —
contracts/openapi.jsonandcontracts/operation-map.jsonkeep Python + TypeScript coverage aligned with the API version - Pre-configured
.mcp.jsonat the repo root — Claude Code auto-loads the server when youcdin - Zero internal-only knowhow — public-grade design with no telemetry, no usage tracking, no error capture, no extension hooks, no read/write gates
What this is
py/dc.py contains:
- A small embedded mini-runtime —
Runtimebase class,@skill_commanddecorator,ArgHelpers(flag parsing, cursor pagination, envelopes),HttpClient(urllib-based) - Two concrete classes:
_DCCore— private helper with_parse_*argument parsers and HTTP business logicDC(Runtime)— public wrapper with@skill_command-decorated methods for every endpoint
The full reference for the underlying API is at https://www.dynamitecircle.com/developers/.
First-time setup
You need a personal API key. Generate one from your DC profile dropdown → DC Member API Key. Then save it:
python3 py/dc.py setup --api-key dk_<api-key>
This writes py/.env.dc (chmod 600). The file is gitignored.
Verify:
python3 py/dc.py self-test
You should see connected as userID[<id>] <Your Name> in the profile step.
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 · 234 lines · 2,961 tokens per session scan C f615e4b03bd2
dc CLAUDE.md is an instructions file published in the GitHub repository dynamitecircle/dc (6 stars, last pushed 27d ago), licensed MIT. It adds 2,961 tokens to every session, about $0.0148 per session on Opus 5. A static security scan graded it C with 3 findings (asks for root, reads agent configuration directories, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
avoid-ai-writing CLAUDE.md
Instructions for conorbronsdon/avoid-ai-writing, covering claude.md, what this is, repository structure, how to make changes and architecture of the skill.
donna-starter AGENTS.md
Instructions for AtlasOmnia/donna-starter, covering agent operating principles, behavior, autonomy — don't pester and working style.
rolecraft AGENTS.md
Instructions for rolecraft-sh/rolecraft, covering rolecraft — development guidelines, ⚠️ startup checklist (read before every task), workflow, interaction rules and code style.
claude-omakase CLAUDE.md
Instructions for gyuch-an02/claude-omakase, covering claude.md, commands, architecture (the big picture), conventions and out of scope.
pencil-skill AGENTS.md
Instructions for Nisus74/pencil-skill, covering pencil-dev-skill: project context, project purpose, naming conventions, repository structure and project context files.
skill.color-expert CLAUDE.md
Claude Code instructions for meodai/skill.color-expert, covering claude.md, project overview, architecture, no build/test/lint and editing guidelines.