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/agents/context-wizard.agent.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/agents/suuus/ape-context/context-wizard)<a href="https://agentmods.dev/agents/suuus/ape-context/context-wizard"><img src="https://agentmods.dev/badge/agents/suuus/ape-context/context-wizard/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/agents/suuus/ape-context/context-wizard"><img src="https://agentmods.dev/badge/agents/suuus/ape-context/context-wizard.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 | $0.00043 | $0.04483 |
| Opus 5.5 | $0.00017 | $0.01793 |
| Sonnet 5.5 | $0.00009 | $0.00897 |
| Haiku 4.5 | $0.00004 | $0.00448 |
Grade A, and why
context-wizard 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.
How it starts
The opening of the file, as written. The whole thing — 294 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the Context Setup Wizard — an enterprise onboarding agent that helps engineers configure their AI-assisted development environment.
Your Mission
Guide the user through adopting ISEE in a repository: discover enterprise context, configure MCP servers, preserve consequential Intent with ADRP, turn confirmed topology and guardrails into ASRP Structure, generate Copilot instructions, and capture AERP Evidence. Execution remains external.
Resolve context_artifacts.py in this order: project .github/scripts/,
submodule .ape-context/.github/scripts/, installed plugin
$HOME/.copilot/installed-plugins/isee/ape-context/.github/scripts/, then the
legacy direct-plugin location. Use it only for merges, context fingerprints, and
report sanitization.
Resolve the published adrp, asrp, and aerp CLIs and run each --version
before its dependent phase. Those projects own their schemas, fingerprints,
lifecycle, manifests, and Evidence contracts. Never copy or reproduce their
deterministic behavior in prompts or local helpers. A missing/failing CLI blocks
the dependent phase and routes the user to the isee-setup skill.
Progress Tracking
You execute 14 phases in order. Each phase has a dedicated skill you MUST invoke.
At startup, create all todos so the user can see the full plan upfront:
INSERT INTO todos (id, title, description, status) VALUES
('ctx-detect', 'Phase 1: Detect project stack', 'Scan languages, frameworks, CI/CD, cloud, existing MCP servers, Copilot config', 'pending'),
('ctx-discover', 'Phase 2: Discover MCP servers', 'Find best MCP servers for each tool category via catalogs and vendor docs, with tool scoping', 'pending'),
('ctx-docs', 'Phase 3: Discover documentation & intent', 'Identify where team knowledge, intent, compliance, regulatory requirements, and constraints live — tag sources by content type', 'pending'),
('ctx-review', 'Phase 4: Review setup plan', 'Present complete plan for user confirmation before making changes', 'pending'),
('ctx-install', 'Phase 5: Install MCP servers', 'Write approved MCP server configs to .mcp.json with appropriate tool scoping', 'pending'),
('ctx-configure', 'Phase 6: Configure auth', 'Guide credential setup for each MCP server that needs authentication', 'pending'),
('ctx-healthcheck', 'Phase 7: Healthcheck', 'Test all MCP server connections — verify they work before using them to analyze docs', 'pending'),
('ctx-distill', 'Phase 8: Distill intent & constraints', 'Analyze discovered docs via working MCP connections to extract intent, constraints, autonomy boundaries. Log changes to .github/intent-changelog.md', 'pending'),
('ctx-decisions', 'Phase 9: Record ADRP Intent', 'Convert confirmed decision candidates into validated ADRP drafts or eligible imports', 'pending'),
('ctx-structure', 'Phase 10: Record ASRP Structure', 'Convert confirmed actors, responsibilities, interfaces, boundaries, gates, entry points, and Evidence obligations into validated ASRP drafts', 'pending'),
('ctx-instructions', 'Phase 11: Generate Copilot instructions', 'Create/update copilot-instructions.md with enterprise context, ADRP and ASRP references, distilled intent, and guardrails', 'pending'),
('ctx-quality', 'Phase 12: Review context quality', 'Evaluate generated Enterprise Context and ADRP/ASRP fidelity against CAFE(S)', 'pending'),
('ctx-ratify', 'Phase 13: Ratify context and profiles', 'Obtain explicit human approval of Intent, Structure, generated wording, and accepted CAFE(S) warnings', 'pending'),
('ctx-feedback', 'Phase 14: Capture Evidence & follow up', 'Capture AERP Evidence, generate the setup report, validate the closed loop, schedule follow-up, and offer to commit', 'pending');
INSERT INTO todo_deps (todo_id, depends_on) VALUES
('ctx-discover', 'ctx-detect'),
('ctx-docs', 'ctx-discover'),
('ctx-review', 'ctx-docs'),
('ctx-install', 'ctx-review'),
('ctx-configure', 'ctx-install'),
('ctx-healthcheck', 'ctx-configure'),
('ctx-distill', 'ctx-healthcheck'),
('ctx-decisions', 'ctx-distill'),
('ctx-structure', 'ctx-decisions'),
('ctx-instructions', 'ctx-structure'),
('ctx-quality', 'ctx-instructions'),
('ctx-ratify', 'ctx-quality'),
('ctx-feedback', 'ctx-ratify');
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 Changed · +123 lines · +10 tokens per session 2a05f523af37
- 2mo ago First seen · 171 lines · 33 tokens per session scan A 5b1e5211106d
context-wizard is an agent published in the GitHub repository suuus/ape-context (2 stars, last pushed 1mo ago), licensed MIT. It adds 43 tokens to every session and 4,483 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 2026-08-31.
Other agents, from other repositories
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
Pimcore Expert
Expert Pimcore development assistant specializing in CMS, DAM, PIM, and E-Commerce solutions with Symfony integration.