Borrowing it
Nothing to install: this file belongs to suuus/ape-context. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/suuus/ape-context/main/.github/skills/context-decisions/SKILL.mdgit clone --depth 1 https://github.com/suuus/ape-contextWrote 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/suuus/ape-context/context-decisions)<a href="https://agentmods.dev/skills/suuus/ape-context/context-decisions"><img src="https://agentmods.dev/badge/skills/suuus/ape-context/context-decisions/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/suuus/ape-context/context-decisions"><img src="https://agentmods.dev/badge/skills/suuus/ape-context/context-decisions.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 | $0.00082 | $0.00474 |
| Opus 5.5 | $0.00033 | $0.00190 |
| Sonnet 5.5 | $0.00016 | $0.00095 |
| Haiku 4.5 | $0.00008 | $0.00047 |
Grade A, and why
context-decisions 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.
What it actually says
Load decision_candidates, decision_sources, and intent. Ordinary facts and
constraints are not decisions. Location proves provenance, not authority.
For candidates present statement, standing, alternatives, four-domain trade-offs,
autonomy, gaps, review trigger; ask Draft, Revise, or Skip. Draft canonical
ape-decision-record/v1 at .github/decisions/drafts/<id>.json with stable ID,
UUID/version, provenance, authority, lifecycle, relationships, and
ratification:null. Never invent missing data.
For ADRP sources present ID/version/fingerprint, URI, status, lifecycle, authority,
scope, and helper assessment; ask Accept, Preserve, or Ignore. Accept requires
eligibility and explicit local scope/authority confirmation. Preserve is inactive.
Future, expired, review-due, terminal, invalid, or untrusted records cannot activate.
Resolve adrp and run adrp --version. Validate with
adrp validate --target and fingerprint with adrp fingerprint --target;
persist decision_drafts. For Accept/Preserve run adrp import,
creating verbatim immutable
.github/decisions/imported/<id>/vNNN.json plus vNNN.source.json. Never inject
retrieval metadata into canonical JSON. Accept supplies basis and confirming
identity. Persist imported_decisions with paths, URI, fingerprint, assessment,
and disposition. Reuse existing record ID/fingerprint; never duplicate.
Drafts and unaccepted imports are not active policy. Failure blocks. Dry-run writes nothing and claims no approval. ADRP owns the schema and deterministic lifecycle; Ape Context must not copy, fork, or silently reimplement it.
What ships with it
4 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 · 37 lines · 82 tokens per session scan A bac7455e02f2
context-decisions is a skill published in the GitHub repository suuus/ape-context (2 stars, last pushed 1mo ago), licensed MIT. It adds 82 tokens to every session and 474 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 2026-10-03.
Other skills, from other repositories
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
playwright-cli
Automate browser interactions, test web pages and work with Playwright tests.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.