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 zoom-outgit 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/zoom-out)<a href="https://agentmods.dev/skills/mattmre/evokore-mcp-public/zoom-out"><img src="https://agentmods.dev/badge/skills/mattmre/evokore-mcp-public/zoom-out/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/zoom-out"><img src="https://agentmods.dev/badge/skills/mattmre/evokore-mcp-public/zoom-out.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 | $0.00043 | $0.01861 |
| Opus 5 | $0.00022 | $0.00931 |
| Sonnet 5 | $0.00009 | $0.00372 |
| Haiku 4.5 | $0.00004 | $0.00186 |
Grade A, and why
zoom-out 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 11d 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 — 151 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Zoom Out
When to use this skill
Use this skill when the current edit window is too low to make a sound design call — you need to see callers, public API surface, or the module boundary one layer above where you are looking. The trigger is "I am unfamiliar with this area" OR "this fix may belong somewhere else." Output is a short reframe paragraph plus a recommendation to keep zooming out or commit the current altitude.
Adapted From Upstream
This adapter is derived from
zoom-out/SKILL.md in
the mattpocock/skills submodule pinned at
90ea8eec03d4ae8f43427aaf6fe4722653561a42. The upstream is a single-line
prompt that says "I don't know this area of code well. Go up a layer of
abstraction. Give me a map of all the relevant modules and callers."
To read the upstream body without loading the full file, prefer:
nav_read_anchor SKILLS/upstream/mattpocock-skills/zoom-out/SKILL.md <anchor-id>
License: MIT, Copyright (c) 2026 Matt Pocock. See repo-root NOTICE and
SKILLS/upstream/mattpocock-skills/LICENSE.
EVOKORE-Specific Adaptations
Concrete deltas vs the upstream prompt:
- No "ask the user" loop. The upstream prompt assumes a human in the
loop will provide the higher-level framing. EVOKORE is autonomous — this
adapter reads prior artifacts instead: the in-flight diff
(
git diff --staged), the active session manifest at~/.evokore/sessions/{sessionId}.json, the replay log at~/.evokore/sessions/{sessionId}-replay.jsonl, and any evidence already captured at~/.evokore/sessions/{sessionId}-evidence.jsonl. nav_get_mapsubstitution for "give me a map". Where the upstream asks the human to provide a map of modules and callers, EVOKORE calls the nativenav_get_maptool against the file under edit (and any obvious caller files surfaced bygit grep) to get a token-efficient anchor map without loading whole files.- Bounded-context awareness. When the file under edit lives inside a
bounded context defined in
docs/adr/0005-bounded-contexts.md, the reframe must name that context explicitly. Going up one layer of abstraction insideSession & Continuityis different from going up one layer insideSkill Registry & Discovery; the seam choice depends on which context's invariants apply. - Composition phrasing for downstream skills. When the reframe
recommends a follow-up, this adapter emits the literal phrasing the
static composition graph parses (e.g., "invoke ubiquitous-language skill"
or "invoke docs-architect skill") so
derive-skill-composition.jscan edge to the correct next step. - Trigger-explicit description. Frontmatter
descriptionis rewritten from the upstream noun-ish phrasing into EVOKORE's "Use when ..." form soresolve_workflowsemantic ranking can find this skill above deep reference leaves.
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.
- 11d ago First seen · 151 lines · 43 tokens per session scan A 74cbc7934b02
zoom-out is a skill published in the GitHub repository mattmre/EVOKORE-MCP-PUBLIC (3 stars, last pushed 3mo ago), licensed MIT. It adds 43 tokens to every session and 1,861 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 2026-08-31.
Other skills, from other repositories
law-of-similarity
Apply the Law of Similarity — shared colour, shape, or size signals that elements belong to one category. Use when signalling relationships across distance. For grouping by position, use law-of-proximity.
law-of-common-region
Apply the Law of Common Region — a shared container, background, or border groups elements regardless of spacing. Use when grouping must survive a tight layout. For grouping by spacing alone, use law-of-proximity.
version-control-strategy
Define version control for design files, components, and libraries — branching, naming, and release. Use when file history is chaotic. For design system contribution rules, use design-system-governance (design-systems).
presentation-deck
Structure a design presentation for a specific audience and decision. Use when presenting internally. For a portfolio narrative use case-study; for the written argument use design-rationale.
accessibility-test-plan
Plan accessibility testing — assistive technologies, participant criteria, WCAG coverage, and session protocol. Use when scheduling testing with real AT users. Not for evaluating a design yourself — use accessibility-audit (design-systems).
diary-study-plan
Design a diary study — prompts, cadence, duration, participant criteria, and analysis frame. Use when behaviour unfolds over days or weeks. For a single-session study, use usability-test-plan.