contexts

A context-gathering router that decides whether a task needs codebase exploration, outside research, or both before coding.

In plain words
What is it for?
Use it to learn how a project is structured, understand how an external tool works, or gather both kinds of information before implementing, fixing, or refactoring.
Why use it?
It removes the guesswork of finding the right background first, helping avoid starting implementation without understanding the project or relevant documentation.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/outlinedriven/odin-codex-plugin/contexts
Any agent
npx skills add OutlineDriven/odin-codex-plugin --skill contexts
Clone the repo
git clone --depth 1 https://github.com/OutlineDriven/odin-codex-plugin

Made for: Claude Code, Codex.

Per session 59 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 967 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00059 $0.00967
Opus 5 $0.00030 $0.00483
Sonnet 5 $0.00012 $0.00193
Haiku 4.5 $0.00006 $0.00097

Measured 2d ago against content hash 37ae9c010b83, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 2d 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

  • contexts — 100% identical, 0 lines differ
skills/contexts/SKILL.md · 78 lines

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:

Read the full file on GitHub · 78 lines

Changes

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.

  1. 2d ago First seen · 78 lines · 59 tokens per session scan A 37ae9c010b83

Subscribe to this mod's changes

contexts is a skill published in the GitHub repository OutlineDriven/odin-codex-plugin (15 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 59 tokens to every session and 967 once invoked, about $0.0003 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 2026-08-30.

Related

Other skills, from other repositories

apm-review-panel

Use this skill to run a multi-persona expert advisory review on a labelled pull request in microsoft/apm. The panel fans out to five mandatory specialists plus a test-coverage specialist (active on every PR that touches src/) plus three conditional specialists (auth, doc-writer, performance-expert), all running in…

microsoft/apm · 178 tokens

batch-bug-shepherd

Use this skill to drive a batch of suspected bugs in microsoft/apm from raw issue list to mergeable PR queue. Fan out one triage subagent per issue (LEGIT / UNCLEAR / FIXED-AT-HEAD), gate every legit bug against PRINCIPLES.md via an apm-ceo strategic-alignment pass, cross-reference legit issues against open PRs, then…

microsoft/apm · 227 tokens

apm-spec-guardian

Use this skill to run a four-panel adversarial advisory review on any pull request that touches the OpenAPM specification artifact (docs/src/content/docs/specs/openapm-.md), its inline / sidecar JSON Schemas (docs/src/content/docs/specs/schemas/.schema.json), or the conformance fixture seed…

microsoft/apm · 215 tokens

apm-triage-panel

Use this skill to triage one microsoft/apm issue selected by the daily sweep, the status/needs-triage fast path, or manual dispatch. Emit one synthesized comment with a decision, label set, exact milestone, and suggested next action.

microsoft/apm · 59 tokens

cli-logging-ux

Use this skill when editing or creating CLI output, logging, warnings, error messages, progress indicators, or diagnostic summaries in the APM codebase. Activate whenever code touches console helpers (richsuccess, richwarning, richerror, richinfo, richecho), DiagnosticCollector, STATUSSYMBOLS, CommandLogger, or any…

microsoft/apm · 94 tokens

pr-description-skill

Use this skill to write the PR description (PR body) for any pull request opened against microsoft/apm. Produces one self-sufficient GitHub-Flavored Markdown artifact: TL;DR, Problem (WHY), Approach (WHAT), Implementation (HOW), 1-3 validated mermaid diagrams, explicit trade-offs, validation evidence, and a…

microsoft/apm · 131 tokens