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 implementation-sessiongit 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/implementation-session)<a href="https://agentmods.dev/skills/mattmre/evokore-mcp-public/implementation-session"><img src="https://agentmods.dev/badge/skills/mattmre/evokore-mcp-public/implementation-session.svg" alt="Measured on agentmods" 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 | $0.00028 | $0.00417 |
| Opus 5 | $0.00014 | $0.00209 |
| Sonnet 5 | $0.00006 | $0.00083 |
| Haiku 4.5 | $0.00003 | $0.00042 |
Grade A, and why
implementation-session 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 4d 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
Implementation Session
This skill executes a complete implementation cycle from planning through orchestration and final session wrap-up.
Core Workflows
1. Priority Identification
- Review
CLAUDE.mdandnext-session.md(or equivalent). - Show the next top 5, or up to top 15 priority items or phases.
- Before implementing anything, review the exact solution we will implement given the parameters to ensure understanding.
2. Stale Local Branches
- Walk through "stale local branches" both locally and in the online repo.
- Ensure they are accounted for in GitHub so we aren't losing anything vital. No short or quick scans.
- Check if local repos have changes that were not merged or committed, or might be from partial sessions that were not completed/logged properly. Fix as needed.
3. Agentic Implementation
- Use agentic orchestration to complete implementation of these items.
- I want no context rot, so please orchestrate and provide agents with instructions and plans as needed to accomplish tasks, then dispose of the agent and use another fresh agent as you move through the work.
- Please research and plan/architect all features before implementation.
- Coordinate analysis of current research and docs within the repo as needed (we have extensive research but may need more).
- If research is done, please make sure to document and save that to the docs folder for tracking and future use.
- Keep track of the session log and agents' work so we can track and monitor.
- Orchestrate and then make a PR for each so we can review.
4. Session Wrap
- Close the session and update the session log.
- Update
next-session.mdand prepare for the next session. - (Keep in mind there may be another session running that just completed; incorporate its handoff points if applicable.)
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.
- 4d ago First seen · 36 lines · 28 tokens per session scan A 36db5329a5a5
implementation-session is a skill published in the GitHub repository mattmre/EVOKORE-MCP-PUBLIC (3 stars, last pushed 3mo ago), licensed MIT. It adds 28 tokens to every session and 417 once invoked, about $0.0001 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
acceptance-orchestrator
Use when a coding task should be driven end-to-end from issue intake through implementation, review, deployment, and acceptance verification with minimal human re-intervention.
mcore-split-pr
Split a PR into multiple PRs to reduce the number of required CODEOWNERS reviewer groups.
create-milestone
Create a GitHub milestone for an upcoming release. Suggests the next version based on the latest release, gathers all merged PRs and closed issues since that release, presents a draft with two tables (Issues and PRs) for user approval, then creates the milestone and assigns all approved items.
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.
nw-finalize
Archives a completed feature to docs/evolution/, migrates lasting artifacts to permanent directories, and cleans up the temporary workspace. Use after all implementation steps pass and mutation testing completes.
fest-execution
Execute active festival tasks. Use when finding the next task, marking tasks completed/blocked/reset, committing with festival traceability, advancing workflow steps, and validating sequence progress.