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 agentmods add skills/lwalden/aiagentminder/scope-checknpx skills add lwalden/AIAgentMinder --skill scope-checkgit clone --depth 1 https://github.com/lwalden/AIAgentMinderWrote 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/lwalden/aiagentminder/scope-check)<a href="https://agentmods.dev/skills/lwalden/aiagentminder/scope-check"><img src="https://agentmods.dev/badge/skills/lwalden/aiagentminder/scope-check.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 | $0.00008 | $0.00616 |
| Opus 5 | $0.00004 | $0.00308 |
| Sonnet 5 | $0.00002 | $0.00123 |
| Haiku 4.5 | $0.00001 | $0.00062 |
Grade A, and why
scope-check 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.
How it starts
The opening of the file, as written. The whole thing — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/aiagentminder:scope-check - Active Scope Governance
Evaluate a proposed feature, task, or change against the project roadmap before you commit to building it.
Use this when you're about to start something and want a clear answer on whether it belongs in the current phase.
How to Use
Describe what you want to build — a sentence or a draft issue title is enough:
/aiagentminder:scope-check— Add dark mode toggle to the settings page
/aiagentminder:scope-check— Refactor the auth middleware to support OAuth providers
What This Command Does
Step 1: Read Context
Read:
docs/strategy-roadmap.md— phase goals, MVP features list, out-of-scope list, future phasesSPRINT.md— if an active sprint exists, check the approved issue list
Step 2: Evaluate
Compare the proposed work against the roadmap and active sprint:
- Is it explicitly listed in the current phase's MVP features? → In scope
- Is it explicitly listed in "Out of Scope"? → Out of scope
- Is it listed in a future phase? → Deferred
- Is it absent from the roadmap entirely? → Not in roadmap
- Does it fall within the approved sprint issues? → In sprint (or Outside sprint if not)
Step 3: Return a Verdict
Return one of these verdicts with a one-sentence recommendation:
In scope:
This aligns with Phase {n} — it maps to "{MVP feature}". Proceed.
Out of scope:
This is marked out of scope in the roadmap: "{quote}". Options: override and proceed, defer to a future phase, or leave it out.
Deferred:
This is planned for Phase {n+1} but not the current phase. Building it now would expand Phase {n} scope. Options: move it up (update the roadmap), or defer until Phase {n+1}.
Not in roadmap:
This isn't in the roadmap. Options:
- Add it to the current phase MVP list (update docs/strategy-roadmap.md)
- Add it to a future phase
- Capture to backlog for later refinement — run
backlog-capture.sh add <type> "<title>" session(see/aiagentminder:backlog)- Mark it explicitly out of scope Which do you prefer?
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 · 69 lines · 8 tokens per session scan A 21fc235a7351
scope-check is a skill published in the GitHub repository lwalden/AIAgentMinder (4 stars, last pushed 1mo ago), licensed MIT. It adds 8 tokens to every session and 616 once invoked, about $0.0000 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
sdd-serve
Serve the SDD Builder's AI request queue: claim requests with sddnextrequest, draft the proposal, answer with sddrespondrequest. Never writes spec files — the user accepts each proposal in the builder. Use when the user asks to attend, serve or listen to the SDD board queue. / Atiende la cola de peticiones del SDD…
sdd-workflow
Guide a project with Spec-Driven Development (SDD) discipline - idea, approved spec, consistent plan, tasks, a gate that verifies approval and consent, implementation, validation, and logbook. Bilingual EN/ES. Use when the user wants to start, spec, plan, implement, or validate work with SDD, or mentions specs, plans…
metrics-instrumentation
Specification for instrumenting an opik-backend workflow with operational OpenTelemetry metrics — per-stage throughput/latency/error counters and native histograms, dimensioned per-customer (workspace). Use when a pipeline (scoring, ingestion, experiments, jobs) needs per-stage visibility. Covers metric emission only…
release
Cut a sim-use release end-to-end. Use when the user runs /release or asks to "ship a release", "publish a version", "cut a release", or "release to homebrew". Drives scripts/local-release.sh; never reimplement its build/sign/tarball logic.
notifications
Send notifications through the unified notification router.
vellum-skills-catalog
Discover bundled skills and search/install community skills from the skills.sh registry.