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.
git clone --depth 1 https://github.com/mattmre/EVOKORE-MCP-PUBLICWrote 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/commands/mattmre/evokore-mcp-public/review-issue)<a href="https://agentmods.dev/commands/mattmre/evokore-mcp-public/review-issue"><img src="https://agentmods.dev/badge/commands/mattmre/evokore-mcp-public/review-issue/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/commands/mattmre/evokore-mcp-public/review-issue"><img src="https://agentmods.dev/badge/commands/mattmre/evokore-mcp-public/review-issue.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 | $0.00008 | $0.01550 |
| Opus 5 | $0.00004 | $0.00775 |
| Sonnet 5 | $0.00002 | $0.00310 |
| Haiku 4.5 | $0.00001 | $0.00155 |
Grade A, and why
review-issue 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 12d 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.
This is a copy
100% identical to review-issue — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 177 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Arguments
$ARGUMENTS: The issue number to review
Your task
Review the specified GitHub issue and help draft an appropriate response based on our community guidelines.
Step 1: Gather issue context
Get the issue details including comments:
gh issue view $ARGUMENTS --repo anthropics/claude-cookbooks --json number,title,body,author,labels,state,comments,createdAt
Step 2: Classify the issue
Determine the issue type based on content:
- Spam/Noise: Gibberish, test posts, off-topic content, or malicious intent
- Bug Report: Reports broken code, links, or incorrect information in cookbooks
- Cookbook Proposal: Proposes new content or significant additions
- Question: Asks about usage, API behavior, or seeks clarification
- Community Resource: Shares external project or resource (redirect to Discord)
- Duplicate: Issue already exists or has been addressed
Step 3: Check for related context
If the issue references specific files or notebooks:
- Read the referenced files to understand context
- Check if the issue is valid (e.g., broken link actually exists)
- Look for related issues or PRs that may address it
Step 4: Draft a response
Based on the issue type, draft an appropriate response following these guidelines:
For Spam/Noise:
- Recommend closing without comment
- Flag any security concerns
For Bug Reports:
- Acknowledge the report and thank the reporter
- Verify the issue if possible (check the referenced file/code)
- If valid and simple: invite them to submit a PR with signed commits
- If valid and complex: acknowledge and indicate it's on our radar
- If already fixed: reference the fix (PR/commit)
- Example: "Thanks for the report! Would you be open to submitting a PR to fix this? If so, please ensure you use signed commits"
For Cookbook Proposals:
- Thank them for the proposal
- Evaluate against our criteria:
- Does it focus on Claude API/SDK capabilities directly?
- Is it practical with clear educational value?
- Is it differentiated from existing content?
- If promising: express interest, ask clarifying questions if needed
- If not a fit: politely explain why, redirect to appropriate resources
- Example redirect: "While [topic] is interesting, we focus on showcasing Claude's native API capabilities. We'd encourage you to think about what specific Claude features you want to demonstrate rather than translating patterns from external frameworks."
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.
- 12d ago First seen · 177 lines · 8 tokens per session scan A 730c96ff5474
review-issue is a command published in the GitHub repository mattmre/EVOKORE-MCP-PUBLIC (3 stars, last pushed 3mo ago), licensed MIT. It adds 8 tokens to every session and 1,550 once invoked, about $0.0000 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to review-issue, differing in 0 lines, and is treated as a copy.
Other commands, from other repositories
plan-sprint
Run a design sprint end to end — challenge framing, schedule, exercises, and prototype test plan.
setup-workflow
Set up a team's operating rhythm end to end — rituals, task flow, tooling, review gates, and version control.
aim-task
Create, view, edit, list, or check off tasks in the AIM workspace.
aim-init
Initialize and sync the AIM project workspace context.
pickup
Pick up a previous hunt on a target — shows hunt history, untested endpoints, and memory-informed suggestions. Usage: /pickup target.com.
speckit.taskstoissues
Convert existing tasks into actionable, dependency-ordered GitHub issues for the feature based on available design artifacts.