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 aep-frameworkgit 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/aep-framework)<a href="https://agentmods.dev/skills/mattmre/evokore-mcp-public/aep-framework"><img src="https://agentmods.dev/badge/skills/mattmre/evokore-mcp-public/aep-framework/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/aep-framework"><img src="https://agentmods.dev/badge/skills/mattmre/evokore-mcp-public/aep-framework.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 | $0.00027 | $0.00868 |
| Opus 5 | $0.00014 | $0.00434 |
| Sonnet 5 | $0.00005 | $0.00174 |
| Haiku 4.5 | $0.00003 | $0.00087 |
Grade A, and why
aep-framework 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 — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AEP Framework (Align-Execute-Prove)
The AEP framework is a structured engineering methodology for agentic workflows. It organizes work into three repeating phases:
The AEP Cycle
1. Align (Scope Lock)
Lock the scope before any work begins. Define the PR range, time window, and inputs. Freeze all references so the cycle operates on a stable baseline.
- Define phase goals and constraints
- Freeze inputs (refinement reports, PR lists, backlogs)
- Document dependencies and risks in
phase-planning.md - Establish acceptance criteria using
templates.md
Phase 1 includes context-and-decisions discipline — see phase-1-context-and-decisions.md.
2. Execute (Implement)
Carry out remediation in severity-tiered order (Critical > High > Medium > Low). Each tier must be fully verified before advancing to the next.
- Generate small, reviewable PRs (one theme per PR)
- Follow branch naming and commit conventions from
templates.md - Select tests per change type using
test-matrix.md - Track progress in the backlog and tracker tables
3. Prove (Verify with Evidence)
Every merged fix requires auditable verification evidence. No tier closes without proof.
- Capture build/test commands and results in
verification-log.md - Evaluate orchestration quality using
evaluation-harness.md - Record pass/fail against golden tasks and metrics
- Archive evidence in session logs
Documents in This Skill
| File | Purpose | AEP Phase |
|---|---|---|
workflow.md |
Full AEP process definition with roles, triggers, and guardrails | All |
templates.md |
Conventions for finding IDs, branches, trackers, and rubrics | Align |
phase-planning.md |
Long-running planning record template for a cycle | Align |
phase-1-context-and-decisions.md |
CONTEXT.md per bounded context + docs/adr/ crystallization with two-pass freeze rule |
Align |
test-matrix.md |
Test selection strategy with agent-specific guidance | Execute / Prove |
verification-log.md |
Evidence tracking for build/test results per PR | Prove |
evaluation-harness.md |
Golden tasks, golden cases, metrics, and evaluation playbook | Prove |
What ships with it
8 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 74 lines · 27 tokens per session scan A 4fad19329483
aep-framework is a skill published in the GitHub repository mattmre/EVOKORE-MCP-PUBLIC (3 stars, last pushed 3mo ago), licensed MIT. It adds 27 tokens to every session and 868 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
ai-observability-promptfoo
Testing and evaluation framework for LLM prompts and applications -- promptfooconfig.yaml, assertions, model-graded evals, red teaming, CI/CD integration, custom providers, and comparative evaluation.
fable-tdd
Drive testable behavior changes and bug fixes through disciplined red-green-refactor cycles with observable regression tests. Use when implementing new features with unit/integration tests, fixing reproducible bugs, modifying business logic, or writing test-first behavior contracts — even if the user does not…
fable-mode
Compatibility alias for the canonical get-fable coding lifecycle. Use when the user explicitly asks for Fable mode or when an existing installation invokes this legacy skill name.
tdd-workflow
Lays out test-driven development as a repeating loop, where a failing test is written first, the smallest code that satisfies it comes next, and a cleanup pass follows once the test is green. Applies when building a new feature, fixing a bug by first capturing it as a failing test, or working through logic intricate…
test-driven-development
Use red-green-refactor, test pyramid discipline, and behavior-focused tests for logic changes and bug fixes.
tdd
Test-driven development with red-green-refactor loop. Use when user wants to build features or fix bugs using TDD, mentions "red-green-refactor", wants integration tests, or asks for test-first development.