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 pattern-learngit 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/pattern-learn)<a href="https://agentmods.dev/skills/mattmre/evokore-mcp-public/pattern-learn"><img src="https://agentmods.dev/badge/skills/mattmre/evokore-mcp-public/pattern-learn.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 | $0.00036 | $0.00473 |
| Opus 5 | $0.00018 | $0.00236 |
| Sonnet 5 | $0.00007 | $0.00095 |
| Haiku 4.5 | $0.00004 | $0.00047 |
Grade A, and why
pattern-learn 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
/pattern-learn — Run ECC Learning Loop
Runs scripts/pattern-extractor.js over current session evidence to extract behavioral patterns. If precision >= 0.70, updates ~/.evokore/patterns/ and optionally injects patterns into MEMORY.md.
Usage
/pattern-learn
/pattern-learn --sessions ~/.evokore/sessions/ --inject
What it does
- Discovers all
*-evidence.jsonlfiles in~/.evokore/sessions/ - Calls
evaluateSession()on each (scripts/eval-harness.js) - Extracts 5 pattern types (PAT-001 through PAT-005) with Laplace confidence
- Applies precision gate: precision >= 0.70 → PROCEED, else ABANDON
- If PROCEED and
--injectflag: writes active patterns to MEMORY.md - Reports: sessions analyzed, patterns extracted, precision, decision gate
Pattern Types
| ID | Pattern | Signal |
|---|---|---|
| PAT-001 | Read before Edit | editsWithPriorRead ratio |
| PAT-002 | Test before Commit | testsBeforeCommit ratio |
| PAT-003 | High error rate → stall | errorRate vs taskCompletion |
| PAT-004 | Subagent → task completion | subagent usage vs completion rate |
| PAT-005 | Purpose set → completion | purposeSet vs taskCompletionRate |
Integration
- Backed by AGT-020 (Neural Optimizer) archetype
- Precision gate is the ECC Phase 4 decision gate (>=70% PROCEED)
- EVOKORE_PATTERN_INJECTION=true enables automatic MEMORY.md injection
- Use
/session-checkpointbefore to ensure evidence is up to date
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 · 47 lines · 36 tokens per session scan A 0aad95bb3a19
pattern-learn is a skill published in the GitHub repository mattmre/EVOKORE-MCP-PUBLIC (3 stars, last pushed 3mo ago), licensed MIT. It adds 36 tokens to every session and 473 once invoked, about $0.0002 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
mnemosyne
Use when curating WrongStack SAGE memory: run deterministic hygiene and anchor verification first, then review contradictions, drift, and noise; file destructive outcomes as review proposals instead of deleting directly.
continuous-learning
Use when a mistake, correction, or surprise taught the workspace something that must stick — a retro or postmortem, the same agent error corrected twice, a resolved bug's root cause, scattered notes-to-self — and route that lesson to the durable surface that fires next time. NOT a forward choice with alternatives…
self-improvement
Captures lessons and promotes recurring patterns.
context-steward
Full context lifecycle — ingest, filter, 3-pass prune, protect, summarize, persist. Load on demand when executing a prune. Triggers are in context-steward-triggers (alwayson).
session-persistence
Maintain continuity across FlowDeck sessions by loading previous context, checkpointing mid-session state, and writing structured summaries at session end.
context-guard
Protect critical context from pruning during compaction. Preserve active plans, safety files, pending operations, and user intent anchors.