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/ferrumclaudepilgrim/claude-code-android/scope-framingnpx skills add ferrumclaudepilgrim/claude-code-android --skill scope-framinggit clone --depth 1 https://github.com/ferrumclaudepilgrim/claude-code-androidWhat 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 | $0.00048 | $0.00463 |
| Opus 5 | $0.00024 | $0.00231 |
| Sonnet 5 | $0.00010 | $0.00093 |
| Haiku 4.5 | $0.00005 | $0.00046 |
Grade A, and why
scope-framing 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 3d 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
Scope Framing
Answer every question before starting research. Write the answers into a brief scope document: one paragraph or a short list per question. Then proceed. If you cannot answer question 1, ask the user before starting.
Required Questions
1. What decision will this research serve? One sentence. Name the decision that will change based on what you find. If no decision is downstream of this research, the research has no purpose. Example: "Whether to use package X or build a custom implementation."
2. Who will act on the findings? Name the actor: a user, an agent, or another system. Different actors need different formats and levels of detail. An agent needs a recommendation. A decision-maker needs tradeoffs. Someone following instructions needs steps.
3. What does "done" look like? Name the specific deliverable that closes this research. Not "I understand the topic" but "a one-page comparison of options A, B, and C with a recommendation." Research without a defined end state expands forever.
4. What is explicitly out of scope? Name at least 2 things you will not research. Naming exclusions forces a scope decision and prevents drift. If you cannot name exclusions, your scope is not defined yet.
5. What would make this research useless? Identify failure modes before you start. Common causes: wrong scope (you answered a related but different question), stale data (the information is outdated for the version in use), missing context (you don't have access to a key constraint that changes the answer).
Output
Write the scope document before doing any research. Save it or include it at the top of your research output. If scope cannot be defined (if question 1 has no answer), stop and ask the user to clarify the decision before you proceed.
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.
- 3d ago First seen · 34 lines · 48 tokens per session scan A 7a1f8ede070c
scope-framing is a skill published in the GitHub repository ferrumclaudepilgrim/claude-code-android (222 stars, last pushed 1mo ago), licensed MIT. It adds 48 tokens to every session and 463 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 2026-08-30.
Other skills, from other repositories
dart-log-failure-parser
Parse failures from Dart and Flutter test logs.
speckit-analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
docs-build
Build, preview, and validate the Uno documentation website (DocFX) locally — surface real content errors vs expected noise, drive rendered pages with Playwright, and validate external-doc commit bumps in importexternaldocs.ps1 before a PR. Use when working under doc/, editing articles/ markdown, bumping an external…
add-sample
Create a SamplesApp sample page with correct theming and attributes. Use when adding UI samples for controls.
speckit-taskstoissues
Convert existing tasks into actionable, dependency-ordered GitHub issues for the feature based on available design artifacts.
auditing-part11-trails
Generates and verifies 21 CFR Part 11-style audit trails — who/what/when, electronic signatures, and tamper-evidence — for OpenMed pipelines in GxP and clinical-trial (GCP) settings. Use when the user runs OpenMed in a regulated/validated environment and needs an attributable, time-stamped, tamper-evident record of…