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/orientnpx skills add ramboz/jig --skill orientgit 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/orient)<a href="https://agentmods.dev/skills/ramboz/jig/orient"><img src="https://agentmods.dev/badge/skills/ramboz/jig/orient.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 | $0.00202 | $0.04230 |
| Opus 5 | $0.00101 | $0.02115 |
| Sonnet 5 | $0.00040 | $0.00846 |
| Haiku 4.5 | $0.00020 | $0.00423 |
Grade A, and why
orient 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 3d 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 — 314 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Orient
One job: tell the user where the project stands and what to do next, in a shape they can actually read.
The user runs /jig:orient (or asks to be oriented) — the calm manager's question,
"where do things stand, and what should I pick up?" Orient answers it by reading
the project's own truth (not guessing), and presenting it in one fixed, scannable
layout: a headline that tells the honest state, then a short stack of titled
sections, each a list of titled bullets — never a wall of inline prose with
items buried mid-sentence.
The substance is grounded; the format is the point. If the answer reads like a paragraph with five things crammed into it, the skill has failed even if every fact is right.
This is a project-level rescan, not a mid-flow nudge. A bare conversational
"what's next?" while actively implementing a slice is asking to continue that slice
— not to re-survey the whole project. Orient is for the deliberate "step back and take
stock" moment (an explicit /jig:orient, a session pickup, a "where are we overall").
Start from the deterministic headline
Do not re-derive the project's lifecycle state by hand — jig already computes it. Run the read-only command spec 088 added and use its line as your factual base:
python3 "${CLAUDE_PLUGIN_ROOT}/skills/spec-workflow/workflow.py" orient --project-dir . --fetch
# → jig hint: <scaffold state> · active specs: <rollup> · focus: <slice needing attention>
# …and, only when the checkout is ahead of its default branch:
# · in flight: <n> commit(s) ahead of <base> on <branch>
# …and, only when the --fetch check finds a problem:
# · freshness: <n> commit(s) behind <base> | could not reach origin
Pass --fetch. Orient reads local boards, ADRs, and slice STATUS — all only as
current as your last fetch — so an interactive orientation must refresh against origin
first, or it will confidently narrate a stale picture (work already shipped on trunk
reported as still open). --fetch runs one bounded, fail-soft git fetch and adds a
freshness: segment when the checkout is behind origin, or when origin could not
be reached (offline: the local view is unverified, not confirmed fresh). This flag is
for the interactive path only — the SessionStart hook never passes it (spec 103's
git-freshness hook already fetches at time-zero), so the hot-path headline is unchanged.
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.
- 3d ago First seen · 314 lines · 202 tokens per session scan A 64c22d3ab944
orient is a skill published in the GitHub repository ramboz/jig (6 stars, last pushed 2d ago), licensed MIT. It adds 202 tokens to every session and 4,230 once invoked, about $0.0010 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
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.
review
Plan-aware graph-enhanced code review before merge. CRITICAL issues block merge. Use after fix/verify.
serena
Serena code intelligence — LSP-powered symbol navigation, diagnostics, and targeted code surgery. Activate before complex refactors, cross-file analysis, or when graph tools need symbol-level depth.
database-migrations
Database migration best practices for schema changes, data migrations, rollbacks, and zero-downtime deployments across PostgreSQL, MySQL, and common ORMs (Prisma, Drizzle, Kysely, Django, TypeORM, golang-migrate).
diagnose
Structured 6-phase debugging. Build feedback loop first, reproduce deterministically, hypothesize with ranked falsifiable theories, instrument one variable at a time, fix with regression test, cleanup. Use when a bug exists, tests fail unexpectedly, or behavior is wrong and cause is unknown.
execute
Dispatch and execute implementation plans with TDD and checkpoints. Use when plan is ready. Parallel by default for independent tasks.