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 skills add OutlineDriven/odin-codex-plugin --skill write-a-skillgit clone --depth 1 https://github.com/OutlineDriven/odin-codex-pluginWrote 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/outlinedriven/odin-codex-plugin/write-a-skill)<a href="https://agentmods.dev/skills/outlinedriven/odin-codex-plugin/write-a-skill"><img src="https://agentmods.dev/badge/skills/outlinedriven/odin-codex-plugin/write-a-skill.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 | $0.00080 | $0.00900 |
| Opus 5 | $0.00040 | $0.00450 |
| Sonnet 5 | $0.00016 | $0.00180 |
| Haiku 4.5 | $0.00008 | $0.00090 |
Grade A, and why
write-a-skill 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- write-a-skill — 97% identical, 1 lines differ
How it starts
The opening of the file, as written. The whole thing — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill authoring loop: gather requirements, draft against the SKILL.md contract, review with the user, refine. One concern per skill; one skill per directory. Apply the skill-creator:skill-creator methodology (three-level progressive disclosure, pushy descriptions, evals.json).
Scope disambiguation
write-a-skill— authors one SKILL.md for one capability inside an existing skills tree.- Repo onboarding — onboards a whole repository, scaffolds AGENTS.md and project conventions.
skill-creator:skill-creator— the upstream methodology this skill applies; consult it for the canonical contract.
Authoring loop
-
Gather requirements — surface decisions before drafting:
- Capability boundary: what task does the skill cover, what does it explicitly not cover?
- Trigger phrases: which user phrases or contexts should load it?
- Determinism: any operation deterministic enough to live in a script rather than re-generated prose?
- Bundled references: docs, schemas, or examples to include?
- Static guarantee context: language family (Rust, TypeScript, Python, Kotlin, Go, OCaml, …) — affects testing-charter scope.
-
Draft the SKILL.md — write to the contract below. Keep body terse and decision-oriented.
-
Review with the user — present the draft, surface ambiguous decisions, and refine.
-
Verify — run any bundled
evals.jsoncases; targeted re-read of the SKILL.md to confirm description triggers and body alignment.
Directory layout
skill-name/
SKILL.md # contract; required
references/ # deeper docs loaded on-demand
REFERENCE.md
EXAMPLES.md
scripts/ # deterministic helpers
helper.{ts,py,sh}
evals.json # trigger / behavior evals
Reference paths in SKILL.md use references/X.md, never ./X.md.
SKILL.md contract
---
name: skill-name
description: <what the skill does>. <when to trigger it — concrete phrases or contexts>.
---
<One-line imperative summary of the skill's posture.>
## <Section> — terse decision-oriented prose
<Body in imperative voice with brief why. ≤200 lines.>
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 · 84 lines · 80 tokens per session scan A 9889d4da257c
write-a-skill is a skill published in the GitHub repository OutlineDriven/odin-codex-plugin (15 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 80 tokens to every session and 900 once invoked, about $0.0004 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 2026-09-03.
Other skills, from other repositories
git-guardrails-claude-code
Install a Claude-Code PreToolUse hook that blocks destructive git commands (push variants including force-push, hard reset, force clean, branch -D, checkout/restore overwrites) before Bash runs them. Use when the user wants git safety rails, force-push prevention, or repository-wipe protection.
duet
Two-party posture — user as director, agent as executor; every fork, tradeoff, or choice surfaced via batched AskUserQuestion with a recommended default. Use when the user invokes /duet, says "ask before" / "pair with me" / "human-in-the-loop", or for aesthetic/architectural/irreversible decisions.
explore
Read-only codebase exploration: discovery, structural reading, and emission of architecture/pattern/tooling/dependency summaries. Use to understand existing code, map files, trace function flow, locate symbols, or build pre-implementation context. Uses a staged 1/3/5 Explore-agent escalation protocol scaled to scope.…
deps-upgrade
Dependency-upgrade campaign — outdated scan, batch-by-severity, breaking-change remediation, lockfile audit. Use when CVEs require remediation, when a major upstream version lands, when stack compatibility forces a sweep, or on a scheduled (quarterly) hygiene cadence. CVE-driven bumps consume security audit findings…
type-driven
Type-driven development. Use when developing with refined types, state machines encoded in types, or proof-carrying types; enforces totality and exhaustive pattern matching.
design-by-contract
Design-by-Contract (DbC) development. Use when implementing with formal preconditions, postconditions, and invariants across any language.