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 templategit 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/template)<a href="https://agentmods.dev/skills/outlinedriven/odin-codex-plugin/template"><img src="https://agentmods.dev/badge/skills/outlinedriven/odin-codex-plugin/template/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/outlinedriven/odin-codex-plugin/template"><img src="https://agentmods.dev/badge/skills/outlinedriven/odin-codex-plugin/template.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 | $0.00069 | $0.00897 |
| Opus 5.5 | $0.00028 | $0.00359 |
| Sonnet 5.5 | $0.00014 | $0.00179 |
| Haiku 4.5 | $0.00007 | $0.00090 |
Grade A, and why
{skill_name} 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- {skill_name} — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.
{skill_name}
{skill_name} is a personal taste skill. It encodes observed taste through 5 evidence-derived anchors, each with a load-bearing concept, canonical exemplar, and two-sided failure boundary.
Posture
{posture_statement}
Conviction with restraint. The anchors are the positive frame; the two-sided charter is the negative space. Side A blocks slop/default convergence. Side B blocks overkill/compensatory excess. Both sides fail by refusing to commit.
Modes [LOAD-BEARING]
Two modes share the auto-clarity exception.
Mode-selection
Auto-detect from invoking-context phrasing, with slash-arg override:
- "is this slop?", "overkill?", "taste-test", "audit this", "review for taste", "what's wrong with this" -> audit.
- "shape this before writing", "load taste", "anchor mode", "before I write" -> anchor.
- Anything else -> audit by default.
- Explicit override:
/{skill_name} audit,/{skill_name} anchor. Override always wins.
audit mode
Walk the 5 anchors against the artifact in hand. For each anchor: verdict (pass / warn / fail), Side A or Side B citation when violated, and concrete fix. Surface tensions when anchors imply conflicting fixes; do not auto-pick a hidden precedence. Close with top-3 ranked fixes.
anchor mode
Load the 5 anchors and two-sided charter as imperatives for subsequent responses. Persistence is best-effort: applies until the user signals "stop taste" or "normal mode" OR context is compacted, whichever comes first. Re-invoke anchor mode if drift is observed.
Two-sided charter
Side A — slop: {side_a_summary}
Side B — overkill: {side_b_summary}
See references/charter.md for the full charter.
Anchors
| Anchor | Influence | Concept |
|---|---|---|
| {anchor_1_name} | {anchor_1_influence} | {anchor_1_concept_short} |
| {anchor_2_name} | {anchor_2_influence} | {anchor_2_concept_short} |
| {anchor_3_name} | {anchor_3_influence} | {anchor_3_concept_short} |
| {anchor_4_name} | {anchor_4_influence} | {anchor_4_concept_short} |
| {anchor_5_name} | {anchor_5_influence} | {anchor_5_concept_short} |
What ships with it
2 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.
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 · 94 lines · 69 tokens per session scan A 9516ce285c61
{skill_name} is a skill published in the GitHub repository OutlineDriven/odin-codex-plugin (14 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 69 tokens to every session and 897 once invoked, about $0.0003 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 2026-08-30.
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.