Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add ramboz/jig/plugin install 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/slice-land)<a href="https://agentmods.dev/skills/ramboz/jig/slice-land"><img src="https://agentmods.dev/badge/skills/ramboz/jig/slice-land.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 5.1 | $0.00130 | $0.03496 |
| Opus 5 | $0.00065 | $0.01748 |
| Sonnet 5 | $0.00026 | $0.00699 |
| Haiku 4.5 | $0.00013 | $0.00350 |
Grade A, and why
slice-land 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.
How it starts
The opening of the file, as written. The whole thing — 300 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Spec 007 created this skill from scratch. The deterministic readiness checks + report generation live in
land.py; this SKILL.md drives the judgment layer (when to invoke, how to interpret blockers, what mode to pick).
What this skill does
Closes the worktree-drift gap: every slice in jig today commits to a worktree branch and stays there until a human remembers to merge. The skill provides a deterministic landing path:
- Verify the slice is actually done — STATUS=DONE in spec.md, full test suite green, deviation log section present, DoD checkboxes all ticked.
- Emit a structured markdown report with five readiness checks
(STATUS=DONE, tests green, deviation log present, DoD ticked, and the
Class-A cross-ref backstop — spec 112: refuse when the slice/ADR is already
integrated on
origin/main,JIG_CROSSREF_GATE=0to bypass) and (in--mode director--mode pr) a Next-steps section of suggested git commands.
prepare is non-destructive on git state: it may read branch state and
fetch origin/main to surface a branch-freshness warning, but it never
switches branches, merges, pushes, or removes worktrees. execute --mode direct runs the destructive merge sequence by pushing the current branch to
origin/main, then fast-forwards the canonical local main worktree to
origin/main or reports why local sync was skipped (slice 007-02 + 081-01);
execute --mode pr runs the destructive push + PR-open sequence (slice
007-03). git worktree remove and gh pr merge are never executed — both
stay user-driven post-landing suggestions.
How to use
Run the readiness check
python3 "${CLAUDE_PLUGIN_ROOT}/skills/slice-land/land.py" prepare \
<path-to-spec.md> <slice-fragment> [--mode {direct,pr}]
spec.md— path to the spec file (e.g.docs/specs/007-slice-land/spec.md).<slice-fragment>— case-insensitive substring against## Slice X — Yheadings. Same lenient match asworkflow.py transition.--mode— optional. Without it, only the readiness check runs.direct— for solo / merge-to-main projects. Suggested commands: push the branch toorigin/main, then fast-forward localmaintoorigin/mainwhen a clean canonicalmainworktree exists.pr— for team / PR-shaped flows. Suggested commands:git push -u origin <branch> && gh pr create --body-file <path>. A PR body is written to/tmp/jig-slice-<NNN-NN>-pr-body.mdcontaining the slice's ACs and a deviation-log excerpt.
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.
- 6d ago First seen · 300 lines · 130 tokens per session scan A 44f749879ce5
slice-land is a skill published in the GitHub repository ramboz/jig (6 stars, last pushed 5d ago), licensed MIT. It adds 130 tokens to every session and 3,496 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.
.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.
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).
execute
Dispatch and execute implementation plans with TDD and checkpoints. Use when plan is ready. Parallel by default for independent tasks.