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 mattmre/EVOKORE-MCP-PUBLIC --skill to-issuesgit 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/skills/mattmre/evokore-mcp-public/to-issues)<a href="https://agentmods.dev/skills/mattmre/evokore-mcp-public/to-issues"><img src="https://agentmods.dev/badge/skills/mattmre/evokore-mcp-public/to-issues/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/mattmre/evokore-mcp-public/to-issues"><img src="https://agentmods.dev/badge/skills/mattmre/evokore-mcp-public/to-issues.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 | $0.00067 | $0.01997 |
| Opus 5 | $0.00034 | $0.00999 |
| Sonnet 5 | $0.00013 | $0.00399 |
| Haiku 4.5 | $0.00007 | $0.00200 |
Grade A, and why
to-issues 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 7d 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 — 205 lines — stays where its author put it; the contents beside it link to each section on GitHub.
to-issues — Decompose a PRD Into Vertical-Slice Issues
When to use this skill
Use when a PRD already exists at docs/prd/<slug>.md (typically produced by
to-prd skill) and the next step is to break it into independently-grabbable,
vertically-sliced GitHub issues. EVOKORE-MCP runs autonomous agent sessions,
so issue decomposition is artifact-driven: read the PRD, emit a slice
manifest, and route shape-critique through panel-of-experts instead of a
live user-approval loop.
If no PRD exists yet, stop. The producer of this work — the to-prd
artifact — must already exist before this skill is entered. If the PRD
exists but has not been panel-reviewed, route it through
panel-of-experts before decomposing.
Adapted From Upstream
This skill is adapted from mattpocock/skills/to-issues (upstream commit
90ea8eec03d4ae8f43427aaf6fe4722653561a42, MIT-licensed). The upstream
skill iteratively asks the user to confirm slice shape, dependency edges,
and acceptance criteria. EVOKORE-MCP replaces those user-loop gates with
a panel-of-experts critique pass and a damage-control-gated filing
flow.
EVOKORE-Specific Adaptations
| Upstream behavior | EVOKORE behavior |
|---|---|
| "Ask the user how to slice" | Read docs/prd/<slug>.md and apply the slice-shape rules below; route uncertainty through panel-of-experts |
| "Iterate until the user approves the slice list" | Invoke panel-of-experts skill with persona set [orchestration-planner, dependency-analyst, scope-cutter] for slice-shape critique |
| "Confirm dependencies with the user" | Read the PRD's ## Dependencies section + ADR cross-links; encode dependencies as issue-number references inside each slice manifest entry |
| "User picks AFK vs HITL" | Heuristic: a slice is AFK if its acceptance criteria are testable by an agent without human input; otherwise HITL |
| "User edits issue bodies" | Issue bodies are markdown files at docs/issue-manifests/<slug>/<slice-id>.md; edit those files, not inline shell strings |
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.
- 7d ago First seen · 205 lines · 67 tokens per session scan A 99935fc9902c
to-issues is a skill published in the GitHub repository mattmre/EVOKORE-MCP-PUBLIC (3 stars, last pushed 3mo ago), licensed MIT. It adds 67 tokens to every session and 1,997 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 2026-09-03.
Other skills, from other repositories
starting-a-new-project
Use when the workspace is empty — no code yet — and the user brings a raw idea: the brand-new branch of setting-up-a-project, normally reached via that dispatcher, directly only when the situation is unmistakable. Not for features in an existing project — use brainstorming instead.
team-workflow
Design the team's operating rhythm — task management, collaboration rituals, and tooling. Use when the day-to-day cadence needs structure. For a time-boxed sprint, use design-sprint-plan.
stakeholder-alignment
Build alignment artifacts — responsibility matrices, decision rights, and communication plans. Use when unclear ownership stalls decisions. For persuading in the moment, use design-negotiation (designer-toolkit).
wrongstack-kanban
Record substantial project work on WrongStack's IPC-backed Kanban board so it survives the session and other agents can see it. Covers card detail, the managed Backlog→Todo→Running→Review→Done lifecycle, lease-fenced dispatch, and what "verified" means before a card reaches Done.
shared-monorepo-nx
Nx monorepo build system — workspace configuration, project graph, task pipelines, caching, generators, plugins, and release management.
shared-monorepo-pnpm-workspaces
Skill "shared-monorepo-pnpm-workspaces" from agents-inc/skills, covering pnpm workspaces for monorepo management, critical: before using this skill, philosophy, core patterns and pattern 1: workspace configuration (pnpm-workspace.yaml).