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 0x0w1/jig --skill jig-readmegit clone --depth 1 https://github.com/0x0w1/jigWrote 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/0x0w1/jig/jig-readme)<a href="https://agentmods.dev/skills/0x0w1/jig/jig-readme"><img src="https://agentmods.dev/badge/skills/0x0w1/jig/jig-readme/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/0x0w1/jig/jig-readme"><img src="https://agentmods.dev/badge/skills/0x0w1/jig/jig-readme.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 | $0.00130 | $0.02002 |
| Opus 5 | $0.00065 | $0.01001 |
| Sonnet 5 | $0.00026 | $0.00400 |
| Haiku 4.5 | $0.00013 | $0.00200 |
Grade A, and why
jig-readme 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 6d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- readme — 95% identical, 2 lines differ
How it starts
The opening of the file, as written. The whole thing — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.
README
Use this skill to create or update the repository's README.md from the actual repository state.
Procedure
- Scan the repository:
- Manifest and build files:
pyproject.toml,package.json,Cargo.toml,go.mod,Makefile, lock files. - Entry points, CLI argument definitions, scripts, and service configs (
Dockerfile,docker-compose*.yml). - Existing documentation under
docs/and usage examples in the code.
- Manifest and build files:
- Classify the project type: CLI tool, library, service/app, or other. The type selects the section layout below when no profile is set.
- Settle the README profile per the Profile Contract below. A profile that resolves replaces the generic defaults for this repository; when none resolves, propose one and continue either way.
- Branch on the current state:
- No
README.md→ create path: draft the README with the section layout below. README.mdexists → update path: check every verifiable claim in the README — commands, options, file paths, links, feature statements — against the repository. Collect mismatches into a drift list, report the list, then apply the fixes. Leave sections that are still accurate untouched.
- No
- Apply the accuracy rules to every line written.
- Run the compression pass from the Compression Rules below:
- Create path: apply it while drafting. Nothing was published yet, so there is nothing to propose.
- Update path: collect the duplication and overstatement into a proposal — name each fact, where it is repeated, and which detail doc would hold it — then ask before moving anything. Report the proposal even when the user declines it.
- Merge the change:
- When the repository has the
develop-task-flowskill (or the installedjig-develop-task-flow), follow it: achore/<slug>branch, a squash merge with adocs:commit, then pushdevelop. - Otherwise propose a normal commit on the current branch.
- When the repository has the
Profile Contract
Two repositories that are the same project type still write their READMEs differently: one keeps a translated mirror, another moves installation into a guide, a third has a table convention its contributors already follow. Those are decisions, not facts the repository can be scanned for, so they are recorded once and read on every later run.
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.
- 6d ago Changed · +72 lines · +41 tokens per session 9d4fd365a051
- 9d ago First seen · 66 lines · 89 tokens per session scan A 870fd170f794
jig-readme is a skill published in the GitHub repository 0x0w1/jig (5 stars, last pushed 6d ago), licensed MIT. It adds 130 tokens to every session and 2,002 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 2026-08-31.
Other skills, from other repositories
rework-rate
Measure and interpret PR rework rate — the emerging 5th DORA metric.
taiyi-ui-design
A design-planning guide for describing how an application's user interface should look and behave. It produces a UI-DESIGN.md document covering layouts, components, interactions, accessibility, and error states.
ln-62-repository-publisher
Commits, pushes, and remotely verifies authorized repository changes. Not for releases, package publication, or announcements.
remove
Remove a deployed framework or addon from the current workspace.
maggy
Maggy is a local AI engineering command center. AI-prioritized inbox across issue trackers (GitHub Issues/Asana), one-click TDD execute with iCPG context enrichment, daily competitor intelligence briefing.
qa-knowledge
To run QA engineering — requirements/gap analysis, scenario & spec design, test implementation, failure triage — over the QA knowledge base.