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 jjdmev2/dme-skills --skill ccthisgit clone --depth 1 https://github.com/jjdmev2/dme-skillsWrote 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/jjdmev2/dme-skills/ccthis)<a href="https://agentmods.dev/skills/jjdmev2/dme-skills/ccthis"><img src="https://agentmods.dev/badge/skills/jjdmev2/dme-skills/ccthis/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/jjdmev2/dme-skills/ccthis"><img src="https://agentmods.dev/badge/skills/jjdmev2/dme-skills/ccthis.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 | $0.00149 | $0.02400 |
| Opus 5 | $0.00075 | $0.01200 |
| Sonnet 5 | $0.00030 | $0.00480 |
| Haiku 4.5 | $0.00015 | $0.00240 |
Grade A, and why
ccthis 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 10d 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 — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ccthis
You are building Linear work end-to-end. Linear is the single source of truth — keep it
updated the WHOLE time, not just at the end. This is a multi-turn conversation: you build, the user
reviews and gives feedback, you iterate. When the work is finished and the user has tested it, they run
/chonchi to hand off for team review (move to In Review, comment, attach the full transcript, and
add the branch/commit link). Do NOT try to export the transcript or close things out from here — that
belongs to /chonchi, at the end.
The unit — EPIC_ID vs WORK_ISSUE_ID
These are different things, and this skill must never conflate them:
- The work issue — a sub-issue of an epic, or a standalone issue — is the unit of building, completion and handoff: one run = one work issue = one branch = one PR.
- The epic is context: the outcome definition, the boundary, the
blockedByorder. It is read, it goes In Progress while any child is being built, and it is NEVER completed or reviewed from here — its state aggregates from its children (/chonchi's job).
Target: the Linear ID the user gave (e.g. /ccthis ENG-45). If it is a work issue, build exactly
that. If it is an EPIC, list its children and build ONE this run — the work issue the user named, or
the first unblocked one — and tell the user which, and which the later runs will be. If a file path like
LINEAR.md was given, read it as the spec. If nothing was given, ask which issue to work. Throughout,
WORK_ISSUE = the one being built this run.
Tooling — use what's installed, never leave a step empty
Prefer gstack skills when available (/spec, /autoplan, /investigate, /code-review, /review,
/qa, /ship, /codex). If a referenced skill is NOT installed, do the equivalent with native tools
(e.g. no /ship → create the PR with git + gh; no /code-review → review the diff yourself).
Never skip a phase because one tool is missing.
The standard (always enforce)
- The units are
/linearthis's: hierarchyProject → Milestone → Epic (labelepic) → Work issues, or a standalone work issue when the work is one package. A code work issue never spans repositories; one repository may have several work issues. Read which repo the WORK_ISSUE targets from the issue itself — never assume an organization topology. - Branch and PR are per WORK ISSUE. A multi-package epic ships as one PR per work issue, across
several runs — never one PR spanning repos, and never a PR that quietly bundles a sibling package.
Respect the epic's
blockedByorder: a frontend slice that renders a field the backend has not shipped yet will not pass its own acceptance criteria. - Work-issue body is
/linearthis's template:## Summary/## Spec/## Acceptance criteria/## Testing steps/## Estimate(a standalone issue adds## Summary (human)+## Why). If the issue you were handed has a different shape, work with what's there — don't reshape it mid-build; use/specif the acceptance criteria are too vague to build against, and update the issue. - Labels: one type (
Feature/Improvement/Bug) +epicon epics +platform:*/ gates as needed. - Completion rule (hard): you may complete ONLY the active work issue, and only once its acceptance criteria are verified. Never mark a sibling work issue Done, never move the epic to Done or In Review, never "tidy up" untouched issues on the way out. Untouched siblings belong to other runs; the epic's state aggregates from its children.
- Definition of Done (work-issue level): its acceptance criteria checked · its PR open and linked ·
the user has tested it · handed off with
/chonchi(In Review + full transcript + branch/commit link) · merged/deployed or follow-ups filed. The EPIC is done only when every child gets there — across runs, not in this one.
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.
- 10d ago First seen · 130 lines · 149 tokens per session scan A 561bb0d3097c
ccthis is a skill published in the GitHub repository jjdmev2/dme-skills (3 stars, last pushed 1mo ago), licensed MIT. It adds 149 tokens to every session and 2,400 once invoked, about $0.0007 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 2026-08-31.
Other skills, from other repositories
cyrus-setup-repository
Add one or more Git repositories to Cyrus configuration so it can process issues from those repos.
artifact-metadata
Manage artifact metadata, versioning, ownership, and review history across the SDLC lifecycle.
steward-prep-delivery
Steward-assisted prep for filing issues and PRs — environment capture, template selection, duplicate detection, delivery-policy compliance check.
contribute-start
Initialize an AIWG contribution workflow by creating a feature branch, configuring DCO, and linking a tracking issue.
ijfw-ship
Use when the user says 'ship it', 'ship this', 'release', 'publish', 'launch', 'deploy', 'go live', 'wrap this up', 'time to ship', or invokes '/ijfw-ship'. Domain-aware release — software (test → tag → push → publish), book (final edit → format → KDP / agent / Substack), campaign (review → schedule → launch →…
split-and-ship
Execute an approved split plan, shipping each change group separately as its own branch and PR or as sequential commits on the current branch. Use when the user asks to "split and ship", "ship the split plan", "create separate PRs", or "split changes into branches".