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-prdgit 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-prd)<a href="https://agentmods.dev/skills/mattmre/evokore-mcp-public/to-prd"><img src="https://agentmods.dev/badge/skills/mattmre/evokore-mcp-public/to-prd/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-prd"><img src="https://agentmods.dev/badge/skills/mattmre/evokore-mcp-public/to-prd.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 | $0.00053 | $0.01988 |
| Opus 5 | $0.00026 | $0.00994 |
| Sonnet 5 | $0.00011 | $0.00398 |
| Haiku 4.5 | $0.00005 | $0.00199 |
Grade A, and why
to-prd 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 8d 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 — 163 lines — stays where its author put it; the contents beside it link to each section on GitHub.
to-prd — Synthesize a PRD From Existing Context
When to use this skill
Use when the next agent step needs a Product Requirements Document but the upstream signal is not a live user dialogue — instead it is some combination of:
- a prior session's
~/.evokore/sessions/*-replay.jsonland~/.evokore/sessions/*-evidence.jsonl - one or more existing
docs/prd/*.mdto revise or merge - an ADR under
docs/adr/describing a contract that must be productized - a triaged bug at
docs/bugs/<slug>.mdwhose fix has product-shaped scope - a panel-of-experts artifact requesting a feature
The output is a markdown PRD at docs/prd/<slug>.md plus a panel-review
invocation. EVOKORE-MCP is agent-driven: the user is not treated as a live
oracle inside this skill. Every "ask the user" step from the upstream
mattpocock/skills/to-prd is rewritten to either read a prior artifact or to
emit a panel invocation.
If you do not have any of the inputs above, stop. Either generate them first
(e.g., run triage-bug, repo-ingestor, or open a panel) or escalate to a
human via the HITL flag (see "Filing the PRD").
Adapted From Upstream
This skill is adapted from mattpocock/skills/to-prd (upstream commit
90ea8eec03d4ae8f43427aaf6fe4722653561a42, MIT-licensed). The upstream
skill assumes a conversational user who iteratively answers requirements
questions and approves the final PRD. EVOKORE-MCP runs autonomous agent
sessions, so the conversational loop has been replaced with artifact reads
and a panel-of-experts review gate.
EVOKORE-Specific Adaptations
The following user-loop steps from upstream have been rewritten:
| Upstream behavior | EVOKORE behavior |
|---|---|
| "Ask the user about goals and non-goals" | Read goals/non-goals from evidence/replay JSONL, ADRs, and any predecessor PRD; if missing, emit a panel-of-experts invocation with personas [product-strategist, technical-architect] |
| "Iterate on user stories until the user approves" | Generate agent stories (since EVOKORE is agent-driven) plus optional user stories, then invoke panel-of-experts skill with persona set [product-strategist, technical-architect, qa-lead] for PRD review |
| "Wait for user feedback before filing" | Write the PRD to docs/prd/<slug>.md and stop. Filing is gated by EVOKORE_AUTO_FILE_ISSUES=true; otherwise the path is emitted for HITL review |
| "Confirm scope with the user" | Read the most recent docs/adr/*.md whose status is Accepted for the relevant bounded context; if scope is ambiguous, route through the panel |
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.
- 8d ago First seen · 163 lines · 53 tokens per session scan A 35dbbb0344b3
to-prd is a skill published in the GitHub repository mattmre/EVOKORE-MCP-PUBLIC (3 stars, last pushed 3mo ago), licensed MIT. It adds 53 tokens to every session and 1,988 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).
write-prd
Write PRD — Product Requirements Documents with structured 8-section templates, user stories, acceptance criteria, and value proposition validation. Use when writing PRDs, defining product requirements, creating user stories with INVEST criteria, or building go/no-go decision frameworks.
product-frameworks
Product management frameworks for business cases, market analysis, strategy, prioritization, OKRs/KPIs, personas, requirements, and user research. Use when building ROI projections, competitive analysis, RICE scoring, OKR trees, user personas, PRDs, or usability testing plans.
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.