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/ramboz/jig/claude-mdgit clone --depth 1 https://github.com/ramboz/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/instructions/ramboz/jig/claude-md)<a href="https://agentmods.dev/instructions/ramboz/jig/claude-md"><img src="https://agentmods.dev/badge/instructions/ramboz/jig/claude-md.svg" alt="Measured on agentmods" 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 | $0.03756 | $0.03756 |
| Opus 5 | $0.01878 | $0.01878 |
| Sonnet 5 | $0.00751 | $0.00751 |
| Haiku 4.5 | $0.00376 | $0.00376 |
Grade A, and why
jig CLAUDE.md 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 4d 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 — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
jig — AI-Native Dev Scaffold
The Claude Code skill pack that scaffolds AI-native development practices. We dogfood the workflow we build.
Hot Cache
Always-loaded primer, kept lean per spec 055/057 (orchestrator context × turns is the cost). This is an index: each bold term is a one-line claim + link; full definitions live in docs/memory/glossary.md + the lexicon and expand on demand via /jig:explain <term>. Update via /jig:memory-sync.
Project codenames / active work
- jig = this skill pack repo (the plugin itself).
- Branch routing —
mainis the sole active line: 1.x and the 2.0 multi-host work both shipped here (latest tagv2.13.0). The legacyv2branch is closed — don't route work to it. See docs/roadmap.md. - Active specs: work has shipped through spec 112 — the status board is the live source, always check it before picking up work. A few parked drafts remain (034 federation-tier, 062 refactor-workflow, 090 immutable-release-bytes, 105 durable-failure-quarantine); 083 lightweight-decision-records is IN_PROGRESS (083-08 Codex host-validation handoff open). Recent load-bearing closures are indexed under Key terms (leanness lens 109, first-class blockers 111, adversarial-register quarantine 110, ref-aware lifecycle + claim reservation 112). Bug-fix repository closure — ADR-0037 (Accepted) / spec 091 — two marker-keyed closure gates on the bug lifecycle;
JIG_BUG_CLOSURE_GATE=0. Per-slice invariants live in the status-board Notes column. Long-horizon-autonomy bridge (oh-my-cli follow-on): spec 106 — autonomy governance plane & identity separation (ADR-0051, Accepted) is built (see the Governance-plane term below); spec 105 — durable failure-quarantine jig-half (ADR-0050, Proposed) is still recorded, not built. servo halves live inramboz/servo(servo specs 023/024/025, ADR-0029/0030) — not yet built. See docs/specs/README.md. Deferred → docs/refinement-todo.md.
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.
- 4d ago First seen · 71 lines · 3,756 tokens per session scan A 5a3246840e23
jig CLAUDE.md is an instructions file published in the GitHub repository ramboz/jig (6 stars, last pushed 4d ago), licensed MIT. It adds 3,756 tokens to every session, about $0.0188 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 instructions, from other repositories
toolshed CLAUDE.md
Claude Code instructions for knitli/toolshed, covering claude.md, what this is, commands, architecture and version sync.
agent-skills AGENTS.md
AGENTS.md instructions for motherduckdb/agent-skills, covering motherduck skills -- agent guide, repo shape, non-negotiable content rules, product defaults to preserve and editing rules.
agent-skills CLAUDE.md
Claude Code instructions for motherduckdb/agent-skills, covering motherduck skills -- claude code context, what motherduck is, default routing, install notes and non-negotiable rules.
agent-skills GEMINI.md
Gemini CLI instructions for motherduckdb/agent-skills, covering motherduck skills for gemini cli, default routing, skill catalog, utility and workflow.
supergraph AGENTS.md
Instructions for datit309/supergraph, covering supergraph — mandatory workflows, skills, auto language detection, tiered workflow — pick the right tier first and full pipeline (tier 3).
frappe-agent copilot-instructions.md
Instructions for Dkm0315/frappe-agent: Treat this repository as Frappe, ERPNext, and Frappe ecosystem guidance for coding agents.