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/ramboz/jig/adr-workflownpx skills add ramboz/jig --skill adr-workflowgit 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/skills/ramboz/jig/adr-workflow)<a href="https://agentmods.dev/skills/ramboz/jig/adr-workflow"><img src="https://agentmods.dev/badge/skills/ramboz/jig/adr-workflow.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 | $0.00122 | $0.05932 |
| Opus 5 | $0.00061 | $0.02966 |
| Sonnet 5 | $0.00024 | $0.01186 |
| Haiku 4.5 | $0.00012 | $0.00593 |
Grade A, and why
adr-workflow 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 5d 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 — 451 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Spec 005 created this skill from scratch. The mechanics live in
adr.py; Claude owns the judgment (what the decision actually says).
What this skill does
Codifies the ADR lifecycle that ADR-0001 and ADR-0002 were written by hand to exercise. Five deterministic operations:
new— scaffolddocs/decisions/adr-NNNN-<slug>.mdfrom the template, with auto-numbering and a slug-collision check. The scaffold carriesstatus: Proposedin frontmatter (from the template) alongside the proseProposed (date)line (spec 073-02 / ADR-0026).accept— stamp the canonicalstatus: Acceptedfrontmatter field and flip the prose Status line toAccepted (YYYY-MM-DD)in the same atomic write. Frontmatter is the authoritative status home; the prose line is a best-effort mirror, rewritten only when it is canonical (spec 073-02 / ADR-0046, which supersedes ADR-0026).supersede— appendSuperseded by [ADR-NNNN](./adr-NNNN-<slug>.md) (date)to an Accepted ADR's Status block andSupersedes ADR-NNNNto the replacement's Status block, and stamp the old ADR'sstatus: Supersededfrontmatter field in the same atomic write (the replacement retainsstatus: Accepted). This is the one edit allowed on an immutable ADR per the Nygard convention. Atomic write on both files.index— regenerate the## Indexsection ofdocs/decisions/README.mdfrom the actual ADR files present. Idempotent. The index is a pure function of the ADR files; see section 4 for what that means for hand-edits and for records it cannot summarize.check-index— read-only audit of that index: exits non-zero if it no longer matches the ADR files, or if two ADRs claim one number. Writes nothing.resolve-todo— strike through a### Decision: ...heading indocs/refinement-todo.mdand append**Resolved by:** [ADR-NNNN: ...](...).
The script does file mutation deterministically. Claude is responsible for the prose inside the ADR (Context, Options Considered, Recommended Decision, Consequences, Open questions).
What ships with it
1 file 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.
- 5d ago First seen · 451 lines · 122 tokens per session scan A 8f00888b945e
adr-workflow is a skill published in the GitHub repository ramboz/jig (6 stars, last pushed 4d ago), licensed MIT. It adds 122 tokens to every session and 5,932 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
onboarding
Skill "onboarding" from knitli/toolshed, covering codeweaver first-run onboarding, your goal, setup flow, 1. welcome & overview and 2. embedding provider selection.
setup
Skill "setup" from knitli/toolshed, covering codeweaver setup / reconfiguration, your goal, setup flow, 1. welcome & context and 2. embedding provider selection.
context-hygiene
Knowledge about AI context file locations, staleness patterns, and maintenance rules across 10+ tool ecosystems. Loaded when working with or near context files.
.codex
Skill ".codex" from knitli/toolshed, covering context hygiene skill, name, description, instructions and 1. discovery.
gh-stack
Manage stacked branches and pull requests with the gh-stack GitHub CLI extension. Use when the user wants to create, push, rebase, sync, navigate, or view stacks of dependent PRs. Triggers on tasks involving stacked diffs, dependent pull requests, branch chains, or incremental code review workflows.
flutter-ui
Build Flutter UI from Figma MCP or image input. Scans src for design tokens (colors, sizes, text styles), existing components, and naming conventions before writing a single line of code. Never hard-codes values.