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 contextsgit 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/contexts)<a href="https://agentmods.dev/skills/outlinedriven/odin-codex-plugin/contexts"><img src="https://agentmods.dev/badge/skills/outlinedriven/odin-codex-plugin/contexts/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/contexts"><img src="https://agentmods.dev/badge/skills/outlinedriven/odin-codex-plugin/contexts.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 | $0.00059 | $0.00967 |
| Opus 5.5 | $0.00024 | $0.00387 |
| Sonnet 5.5 | $0.00012 | $0.00193 |
| Haiku 4.5 | $0.00006 | $0.00097 |
Grade A, and why
contexts 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:
- contexts — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Context Command
Auto-router for pre-implementation context gathering. Classify the input as codebase-oriented, doc-oriented, or both; invoke the appropriate workflow; emit a detected: acknowledgement as the first output line.
When to Apply / NOT
Apply:
- Any request for context, background, or orientation before implementing, fixing, or refactoring
- "How does X work", "get me context on Y", "what's the architecture of Z"
NOT apply:
- Bug reproduction or root-cause investigation — use a debugging workflow
- Already-in-progress implementation — gather context first, then proceed
- Analysis-only output with no pre-implementation intent
Detected Mode Acknowledgement [LOAD-BEARING]
First output line before ANY work:
detected: <mode> — scope=<paths|libs|both> sources=<brief summary>
Mode values: code-ref, doc-ref, both, ambiguous.
For both mode, also append: (sequential dispatch: codebase first, then external)
Input Classifier
First-match wins. Check in order: both must come before leaf modes so mixed-signal inputs are reachable.
| Priority | Mode | Minimum condition |
|---|---|---|
| 1 | both |
Repo-local signal (path, glob, symbol, or module) AND external signal (library, framework, SDK, API, CLI, or service name) both present and non-trivial |
| 2 | code-ref |
Repo-local signal present; no external signal |
| 3 | doc-ref |
External signal present; no repo-local signal |
| 4 | ambiguous |
Neither signal cleanly detected, OR signals present but neither dominant |
Worked examples:
"How does our /autoresearch skill use LangGraph's interrupt for HITL pauses?"→ repo signal + external signal →both"Refactor claude/skills/contexts/SKILL.md"→ repo signal only →code-ref"Latest Pydantic v2 model_validator signature"→ external signal only →doc-ref"Give me context on routing"→ no concrete signal →ambiguous→ gate fires
Auto-Detect Gate
Fire AskUserQuestion (single-select, NEVER multiSelect) when classifier returns ambiguous OR when both signals are present but one is dominant and the mode is unclear:
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 · 78 lines · 59 tokens per session scan A 37ae9c010b83
contexts is a skill published in the GitHub repository OutlineDriven/odin-codex-plugin (14 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 59 tokens to every session and 967 once invoked, about $0.0002 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.