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 scope-lockgit 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/scope-lock)<a href="https://agentmods.dev/skills/mattmre/evokore-mcp-public/scope-lock"><img src="https://agentmods.dev/badge/skills/mattmre/evokore-mcp-public/scope-lock/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/scope-lock"><img src="https://agentmods.dev/badge/skills/mattmre/evokore-mcp-public/scope-lock.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 | $0.00034 | $0.00586 |
| Opus 5 | $0.00017 | $0.00293 |
| Sonnet 5 | $0.00007 | $0.00117 |
| Haiku 4.5 | $0.00003 | $0.00059 |
Grade A, and why
scope-lock 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 6d 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.
/scope-lock — Lock Session Scope
Writes a scope constraint to the session manifest and injects it into purpose-gate's additionalContext on every subsequent prompt. Optionally adds a temporary damage-control rule blocking out-of-scope file types.
Usage
/scope-lock "Implement TrustLedger only — no other src/ files"
/scope-lock "Fix failing tests in tests/integration/ only"
What it does
- Writes the scope description to the session manifest as
scopeLock: { description, lockedAt } - On the next prompt, purpose-gate reads the scope lock and prepends it to
additionalContext - Optionally: creates a temporary damage-control rule scoped to this session
Scope Lock Format in Manifest
{
"scopeLock": {
"description": "Implement TrustLedger only — no other src/ files",
"lockedAt": "2026-04-15T03:00:00Z",
"sessionId": "sess-abc123"
}
}
How to set scope manually
Until this skill is fully wired into the purpose-gate hook, set scope by adding to session manifest:
// In purpose-gate.js subsequent-prompt branch, after loadPolicyBundle():
const manifestPath = path.join(SESSIONS_DIR, sessionId + '.json');
let scopeLock = null;
try {
const manifest = JSON.parse(fs.readFileSync(manifestPath, 'utf8'));
scopeLock = manifest.scopeLock || null;
} catch {}
if (scopeLock) {
contextParts.push('## Scope Lock\n' + scopeLock.description + '\n(locked at ' + scopeLock.lockedAt + ')');
}
Clearing scope lock
To clear a scope lock:
const manifest = JSON.parse(fs.readFileSync(manifestPath, 'utf8'));
delete manifest.scopeLock;
fs.writeFileSync(manifestPath, JSON.stringify(manifest, null, 2));
Or start a new session with /session-checkpoint + new session ID.
Integration
- Works with purpose-gate.js ContinueGate: scope lock overrides the keyword alignment check
- Works with AGT-018 (Governance Gate): scope lock is included in PolicyBundle fingerprint
- Pairs with
/session-checkpointto save state before locking scope
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.
- 6d ago First seen · 74 lines · 34 tokens per session scan A 96381130fd6a
scope-lock is a skill published in the GitHub repository mattmre/EVOKORE-MCP-PUBLIC (3 stars, last pushed 3mo ago), licensed MIT. It adds 34 tokens to every session and 586 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
morning
Use when performing daily status check-ins, PR reviews, and morning workflow routines.
brain-capture
Quickly capture tasks, ideas, and notes with smart metadata inference. Use when the user says "remind me", "save this", "add a task", "I need to", "don't let me forget", or any variant of quick capture.
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.
03_task5
Triages a support inbox, prioritizes urgent issues, routes each to the right internal team member, and drafts any customer-facing replies for review. Use when: catching up on a backlog of support messages, producing an escalation report, or routing issues to appropriate owners.
proposals
Use when writing the document a buyer reads to say yes — a commercial proposal or Statement of Work, turning discovery notes into a scoped and priced document, adding tiers so the middle one wins, or diagnosing a proposal that will not close. NOT the binding legal agreement with its liability and IP clauses (that is…
lark-workflow-standup-report
A workflow that combines calendar events with unfinished Lark tasks to produce a daily or weekly work summary.