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/dynamitecircle/dc/pynpx skills add dynamitecircle/dc --skill pygit 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 | $0.00078 | $0.04308 |
| Opus 5 | $0.00039 | $0.02154 |
| Sonnet 5 | $0.00016 | $0.00862 |
| Haiku 4.5 | $0.00008 | $0.00431 |
Grade B, and why
dc scanned grade B with 1 finding 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 yesterday.
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.
# Save it (writes .env.dc next to the client, chmod 600, gitignored) How it starts
The opening of the file, as written. The whole thing — 543 lines — stays where its author put it; the contents beside it link to each section on GitHub.
DC Member API Skill
Read and act on your own Dynamite Circle membership data via the public DC
Member API at https://api.dynamitecircle.com — your profile, trips, events,
tickets, invites, inbox, rooms, chapters, announcements, and locator digest.
Reads and writes are always scoped to you (the owner of the API key).
There are two ways to use it, and one of them needs nothing installed:
| Path | What it is | Pick it when |
|---|---|---|
| Local client (this file) | One stdlib-only Python file: a CLI (dc …), a Python library (from dynamitecircle import DC), and a local stdio MCP server (dc --mcp) |
You're an agent that can run Python or shell — you get a CLI, scriptable library calls, and a local server you can pin/run offline |
| Hosted MCP | A remote MCP endpoint: https://api.dynamitecircle.com/mcp (Streamable HTTP) |
You're an MCP-capable chat app and want zero install + always-current tools (no updates to manage) |
Rule of thumb for an agent: if you can execute commands, prefer the local
client (richest: CLI + library + MCP, works offline, version-pinnable). If
you're a hosted assistant that only speaks MCP, use the hosted URL. Both
authenticate with the same dk_ key.
Install the local client
Three ways to get the client, from quickest to most isolated:
# A) PyPI — quickest. Gives you the `dc` command + the importable library.
pip install dynamitecircle # CLI + library
pip install 'dynamitecircle[mcp]' # + local MCP server (dc --mcp)
# B) uvx — no install, auto-updates on every run (great for an MCP config)
uvx --from 'dynamitecircle[mcp]' dc --help
# C) Clone — full repo (MCP config, docs, vendor via submodule/subtree)
git clone https://github.com/dynamitecircle/dc.git && cd dc
Command form in this doc: examples use the installed
dccommand. From a clone, replacedcwithpython3 py/dc.py(e.g.python3 py/dc.py profile).
Setup (get + save your key)
Each member needs their own personal API key. Generate one from the DC
profile dropdown → DC Member API Key. Keys look like dk_<api-key> and
are revocable from the same dropdown.
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- yesterday First seen · 543 lines · 78 tokens per session scan B 39786a3bc5c8
dc is a skill published in the GitHub repository dynamitecircle/dc (5 stars, last pushed 27d ago), licensed MIT. It adds 78 tokens to every session and 4,308 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
partner-skill-compiler
Partner skill compiler authority — synthesize grounded public evidence into a reusable partner prompt, persona profile, and SKILL.md with worldview, operating style, audience, offers, voice anchors, and strict anti-hallucination constraints.
image-to-code
Elite website image-to-code skill for Codex. For visually important web tasks, it must first generate the design image(s) itself, deeply analyze them, then implement the website to match them as closely as possible. In Codex, it must prefer large, readable, section-specific images instead of tiny compressed boards…
convex-billing
Add Stripe billing/payments to the Convex app via @convex-dev/stripe (checkout + webhook + gating).
edgeone skill scanner
Scan any agent skill for security risks before you install or use it. Powered by Tencent Zhuque Lab A.I.G (AI-Infra-Guard). 100% local static analysis — no file contents or credentials leave your device. Compatible with CodeBuddy, Cursor, Windsurf, Claude Code, OpenClaw and more. Triggers on: 这个 skill 安全吗, skill 安全扫描…
dev-workflow
The complete development workflow for SkillHub contributors including local dev, staging validation, testing, and PR creation. Ensures agents follow the correct sequence of steps.
convex-performance-audit
Audits Convex performance for reads, subscriptions, write contention, and function limits. Use for slow features, insights findings, OCC conflicts, or read amplification.