Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/wyattowalsh/agentsnpx agentmods add skills/wyattowalsh/agents/justfileWrote 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/wyattowalsh/agents/justfile)<a href="https://agentmods.dev/skills/wyattowalsh/agents/justfile"><img src="https://agentmods.dev/badge/skills/wyattowalsh/agents/justfile/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/wyattowalsh/agents/justfile"><img src="https://agentmods.dev/badge/skills/wyattowalsh/agents/justfile.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 | $0.00088 | $0.01805 |
| Opus 5.5 | $0.00035 | $0.00722 |
| Sonnet 5.5 | $0.00018 | $0.00361 |
| Haiku 4.5 | $0.00009 | $0.00180 |
Grade A, and why
justfile 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 1mo 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 — 177 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Justfile
Author and maintain Just task runners. House style matches this repo's root
justfile: minimum-version ≥ 1.55.0, default-list, require(),
[default] / [doc] / [group] / [arg], prefer [script] for multi-line
bodies. Distill casey/Just principles; never paste third-party skill prose or
embed the casey README.
Load reference files on demand from the index below — do not load all at once. Frontmatter is for discovery; references carry deep procedure.
Permission posture
write-scoped — may write justfiles; read-only just inspect by default; ask
before destructive recipes, deleting a Makefile, or running side-effecting
recipes.
Dispatch
| $ARGUMENTS | Mode |
|---|---|
(empty) / help |
Empty-args gallery |
create [description] |
Create |
edit [path|recipe] |
Edit |
migrate [source] |
Migrate |
check [path] |
Check |
discover [query] |
Discover |
| Natural language about justfiles | Auto-detect |
Auto-detection heuristic
- Existing
justfile/Justfile+ modify/fix/rename → edit - "migrate" / Makefile /
package.jsonscripts → just → migrate - "lint" / "check" / "fmt" / house-style audit → check
- "list" / "show" / "what recipes" / dump → discover
- New justfile or "add recipe" without existing file → create
- Pure shell / CI YAML / Make build semantics / mise / Compose → refuse (see negatives)
Empty args
When $ARGUMENTS is empty, show the mode gallery, posture line, critical rules
summary, and reference index. Do not invent a mutating default.
Canonical vocabulary
Use these exactly (canonical terms):
| Term | Meaning |
|---|---|
write-scoped |
May write justfiles; ask before destructive runs/deletes |
| house style | This repo's justfile conventions (default-list, [doc], [script], …) |
| discover | Read-only inspect via just --list / --show / --dump |
| migrate | Map Makefile/npm task scripts into Just recipes |
[script] |
Multi-line script recipe attribute (never combine with recipe-level @) |
| opt-in gate | Create-mode confirmations before overwrite or side effects |
What ships with it
45 files 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.
- evals/_drafts/explicit-check.json 560 B
- evals/_drafts/explicit-create.json 691 B
- evals/_drafts/explicit-discover.json 528 B
- evals/_drafts/explicit-edit.json 616 B
- evals/_drafts/explicit-empty-gallery.json 565 B
- evals/_drafts/explicit-migrate.json 621 B
- evals/_drafts/implicit-justfile-nl.json 724 B
- evals/_drafts/neg-ci-yaml.json 473 B
- evals/_drafts/neg-docker-compose.json 481 B
- evals/_drafts/neg-make-file-build.json 608 B
- evals/_drafts/neg-mise-toolchain.json 570 B
- evals/_drafts/neg-pure-shell.json 580 B
- evals/_drafts/safety-delete-makefile.json 593 B
- evals/_drafts/safety-secrets-in-justfile.json 568 B
- evals/evals.json 9.3 KB
- evals/explicit-check.json 469 B
- evals/explicit-create.json 520 B
- evals/explicit-discover.json 438 B
- evals/explicit-edit.json 509 B
- evals/explicit-empty-gallery.json 388 B
- evals/explicit-migrate.json 483 B
- evals/implicit-justfile-nl.json 581 B
- evals/neg-ci-yaml.json 396 B
- evals/neg-docker-compose.json 375 B
- evals/neg-make-file-build.json 488 B
- evals/neg-mise-toolchain.json 456 B
- evals/neg-pure-shell.json 479 B
- evals/safety-delete-makefile.json 472 B
- evals/safety-secrets-in-justfile.json 441 B
- references/check.md 2.3 KB
- references/create.md 2.8 KB
- references/discover.md 2.6 KB
- references/edit.md 2.4 KB
- references/migrate.md 2.8 KB
- references/patterns.md 2.4 KB
- references/pitfalls.md 2.3 KB
- references/when-not-just.md 2.1 KB
- scripts/asset_toolkit/__init__.py 303 B runs code
- scripts/asset_toolkit/_shared.py 5.6 KB runs code
- scripts/asset_toolkit/common.py 3.1 KB runs code
- scripts/asset_toolkit/package.py 43 KB runs code
- scripts/asset_toolkit/validate_evals.py 11 KB runs code
- scripts/asset_toolkit/validate_hooks.py 13 KB runs code
- scripts/asset_toolkit/validate_skill.py 3.6 KB runs code
- scripts/check.py 1.6 KB runs code
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.
- 1mo ago First seen · 177 lines · 88 tokens per session scan A 46271edbce38
justfile is a skill published in the GitHub repository wyattowalsh/agents (5 stars, last pushed 1mo ago), licensed MIT. It adds 88 tokens to every session and 1,805 once invoked, about $0.0004 per session on Opus 5.5. 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 2026-09-03.
Other skills, from other repositories
story-readiness
Is a story implementation-ready? Checks clear acceptance criteria, open questions, ADR refs. READY/NEEDS WORK/BLOCKED/NOT ASSESSED.
recipe-create-meet-space
Create a Google Meet meeting space and share the join link.
workthreads
SpecStory Workthreads - a weekly work-thread rollup across a team's repos from SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more). It groups the window's sessions into threads of work per project and labels each new / open / recently closed, so a lead sees what shipped, what is still…
atmos-config
Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.
ring:mapping-feature-relationships
Mapping how features relate and phasing the work: categorizing PRD features, grouping them into domains, charting cross-feature journeys, dependencies, and integration points, and defining the binding Phases that plan.md mirrors one-to-one at Gate 7. Gate 2 of ring:planning-large-features; runs after…
handle-linkedin-connection-request-signal
Use this skill when someone sends a team member an inbound LinkedIn connection request. An inbound request is a deliberate, ACTIVE first-party intent signal — meaningfully stronger than a passive profile view — and it deserves different scoring rules. The skill resolves and enriches the requester, gates them through…