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 skills add BIAsia/c2d2c --skill ds-governgit clone --depth 1 https://github.com/BIAsia/c2d2cWrote 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/biasia/c2d2c/ds-govern)<a href="https://agentmods.dev/skills/biasia/c2d2c/ds-govern"><img src="https://agentmods.dev/badge/skills/biasia/c2d2c/ds-govern/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/biasia/c2d2c/ds-govern"><img src="https://agentmods.dev/badge/skills/biasia/c2d2c/ds-govern.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 | $0.00112 | $0.01147 |
| Opus 5 | $0.00056 | $0.00574 |
| Sonnet 5 | $0.00022 | $0.00229 |
| Haiku 4.5 | $0.00011 | $0.00115 |
Grade A, and why
ds-govern 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 — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
c2d2c:ds-govern — converge + freeze
Project parameters
Resolve parameters from C2D2C.md at the repo root (fallback: .claude/c2d2c.md); if absent, offer to bootstrap one from the template at ../../templates/C2D2C.template.md (plugin root; standalone installs without that file fetch https://raw.githubusercontent.com/BIAsia/c2d2c/main/templates/C2D2C.template.md). This skill uses TOKEN_HOME, SPEC_HOME, GATE_HOME, LAW_HOME, DS_ROUTE, TOKEN_EXPORT, GATES.
Core mental model: governance = convergence + freezing. Convergence without freezing drifts back within months; freezing without cleanup leaves two systems that mislead everyone who comes later. One governance pass must complete all five moves: single source, full migration, gate, dead-code removal, written rule.
0. Decide to govern
Trigger signals: the third hand-written variant of the same style; reviews correcting the same class of mistake repeatedly; a restore job discovering "this value exists five ways in the codebase". Scope first: which dimension (radius/shadow/color/spacing/a component API), which directories, which areas are exempt (demos/marketing pages/vendored code, usually).
1. Full-repo census
rgevery current spelling of the dimension into a list: each form × occurrence count × representative file.- Derive the "rungs actually in use" from the list. The ladder grows out of usage, not out of thin air.
- Separate the exceptions: legitimate special cases (future exemption areas) vs. drift (to migrate).
2. Write the spec (STOP: user review)
Write the system doc in SPEC_HOME, covering:
- The ladder/recipe: fixed token table (e.g. a px-value radius ladder, a three-tier shadow recipe) and when each rung applies.
- Single source: where values live (tokens) and where logic lives (single-source modules like
field-shell.ts,tone.ts). - The ban list: which spellings become illegal (raw literals, raw palette classes, inline beziers…).
- Exemptions: directory-level exemptions plus allowlist semantics (the allowlist is a frozen baseline, not a door: existing debt may sit in it; new code may not enter).
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 · 68 lines · 112 tokens per session scan A d2d56f7998bb
ds-govern is a skill published in the GitHub repository BIAsia/c2d2c (54 stars, last pushed 1mo ago), licensed MIT. It adds 112 tokens to every session and 1,147 once invoked, about $0.0006 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 2026-08-30.
Other skills, from other repositories
recipe-create-meet-space
Create a Google Meet meeting space and share the join link.
workthreads
SpecStory Workthreads - a weekly work-thread rollup across a team's repos from SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more). It groups the window's sessions into threads of work per project and labels each new / open / recently closed, so a lead sees what shipped, what is still…
atmos-config
Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.
story-readiness
Validate that a story file is implementation-ready. Checks for embedded GDD requirements, ADR references, engine notes, clear acceptance criteria, and no open design questions. Produces READY / NEEDS WORK / BLOCKED verdict with specific gaps. Use when user says 'is this story ready', 'can I start on this story', 'is…
autotask-creator
Rules for automation CRUD from the group-chat commander. The commander does not call mutation tools and does not edit cloud/autotasks files directly. It emits one or more top-level ... containers in its final text; the bus parses and applies them after the turn.
projects
List all managed projects with status, branch, open PRs, and open issue counts — portfolio-level view.