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 xD4O/praxis --skill scopinggit clone --depth 1 https://github.com/xD4O/praxisWrote 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/xd4o/praxis/scoping)<a href="https://agentmods.dev/skills/xd4o/praxis/scoping"><img src="https://agentmods.dev/badge/skills/xd4o/praxis/scoping/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/xd4o/praxis/scoping"><img src="https://agentmods.dev/badge/skills/xd4o/praxis/scoping.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 | $0.00108 | $0.00959 |
| Opus 5.5 | $0.00043 | $0.00384 |
| Sonnet 5.5 | $0.00022 | $0.00192 |
| Haiku 4.5 | $0.00011 | $0.00096 |
Grade A, and why
scoping 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 15d 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 — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Scoping Protocol
EXTREMELY_IMPORTANT: This is a MANDATORY protocol, not a suggestion. Follow every step. Do not skip steps. Do not combine steps. Do not summarize. Work through each gate in order.
Scope creep is not a discipline failure — it is a definition failure. If nothing was declared OUT, everything is arguably IN. This protocol forces the boundary before a line of code makes it expensive to move.
STEP 1 — Enumerate candidate capabilities
List every capability the request could plausibly include — including the ones the user did not say but would expect, and the ones they might be assuming are free but are not. A short list here means you are scoping your first idea, not the problem.
STEP 2 — Classify each MUST / SHOULD / WON'T-THIS-VERSION
Every capability gets exactly ONE label:
- MUST — the thing is useless or incoherent without it.
- SHOULD — real value, but the thing works and ships without it.
- WON'T (this version) — explicitly deferred or excluded, on purpose.
If everything is a MUST, you have not scoped — you have re-listed the request.
STEP 3 — The WON'T list must be non-empty
Look at what you cut. If the WON'T list is empty, either the scope is genuinely tiny (say so and show why) or you have not drawn a boundary — draw one now. A scope with no edges is the thing that ships three months late.
STEP 4 — Write an acceptance criterion for every MUST
Each MUST needs an observable acceptance test — "a user can X and sees Y", checkable by someone other than you. A MUST you cannot write acceptance for is not defined yet; refine it until you can, or it is not actually a MUST.
STEP 5 — Report
SCOPE: [what is being built]
├── MUST: [capability → acceptance criterion, one line each]
├── SHOULD: [deferred-but-valuable capabilities]
├── WON'T (this version): [explicitly excluded — non-empty]
├── The cut line: [one sentence: what makes this version done]
└── Confidence: [HIGH / MEDIUM / LOW]
Confidence: HIGH — MUSTs all have acceptance criteria, cut line is unambiguous. MEDIUM — some boundaries depend on unvalidated user need. LOW — you cannot tell a MUST from a SHOULD without input the user has not given; ask before building.
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.
- 15d ago First seen · 88 lines · 108 tokens per session scan A a9e17fc631c7
scoping is a skill published in the GitHub repository xD4O/praxis (28 stars, last pushed 2mo ago), licensed MIT. It adds 108 tokens to every session and 959 once invoked, about $0.0004 per session on Opus 5.5. 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 2026-10-02.
Other skills, from other repositories
story-readiness
Is a story implementation-ready? Checks clear acceptance criteria, open questions, ADR refs. READY/NEEDS WORK/BLOCKED/NOT ASSESSED.
recipe-create-meet-space
Create a Google Meet meeting space and share the join link.
atmos-config
Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.
workthreads
SpecStory Workthreads - a weekly work-thread rollup across a team's repos from SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more). It groups the window's sessions into threads of work per project and labels each new / open / recently closed, so a lead sees what shipped, what is still…
projects
List all managed projects with status, branch, open PRs, and open issue counts — portfolio-level view.
remove
Remove a deployed framework or addon from the current workspace.