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 alonf/specrew --skill stable-scope-effort-estimationgit clone --depth 1 https://github.com/alonf/specrewWrote 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/alonf/specrew/stable-scope-effort-estimation)<a href="https://agentmods.dev/skills/alonf/specrew/stable-scope-effort-estimation"><img src="https://agentmods.dev/badge/skills/alonf/specrew/stable-scope-effort-estimation/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/alonf/specrew/stable-scope-effort-estimation"><img src="https://agentmods.dev/badge/skills/alonf/specrew/stable-scope-effort-estimation.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00028 | $0.00958 |
| Opus 5.5 | $0.00011 | $0.00383 |
| Sonnet 5.5 | $0.00006 | $0.00192 |
| Haiku 4.5 | $0.00003 | $0.00096 |
Grade A, and why
stable-scope-effort-estimation 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 1mo 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 — 44 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Context
Use this skill when planning an iteration that follows a completed phase-closure. If the prior phase's clarity, specification, and planning work is stable and complete, subsequent iterations can be estimated with high accuracy because task boundaries are clear, dependencies are known, and no discovery surprises are likely.
Iteration 002 of feature 005 validated this: all 7 tasks delivered at estimated effort (zero variance, zero rework) because Phase 1 was fully clarified before iteration started. No mid-execution discoveries of missing scope, broken assumptions, or hidden blockers emerged.
Updated with Iteration 001 (feature 007) evidence (2026-05-11): Documentation-heavy Foundation & Governance iteration delivered 10/10 story points at estimated effort with zero variance and zero rework. Phase 1 + Phase 2 scope (coordinator prompt, templates, decision guidance, Squad.agent.md codification, governance checklist, soft-validator design) was fully specified in planning artifacts with clear acceptance criteria for each task. No mid-execution scope creep or discovery surprises. This validates the pattern extends beyond Phase-N feature implementation to governance-infrastructure and prompt-engineering tasks where scope clarity is achievable.
Patterns
- Precondition: Phase clarity is complete. Before starting an iteration, verify the prior phase's specification, clarifications, and key assumptions are frozen and recorded. If the phase still has open questions, defer the iteration.
- Precondition: Task boundaries are clear. Read each task's requirement row, owner, and acceptance criteria. If a task owner still needs clarification on what "done" means, the iteration is premature.
- Estimate at historical accuracy. When preconditions are met, estimate effort using historical patterns from similar tasks. Variance approaches zero.
- Track actual effort, not elapsed time. Record what effort (in story_points, hours, or whatever unit your team uses) each task actually consumed, not when the calendar says it started or ended.
- When discovery happens, log it explicitly. If an iteration discovers a hidden scope gap, record it as a drift event with the resolution (spec-updated, implementation-reverted, deferred, or human-decision). This preserves estimation feedback for next time.
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.
- 1mo ago First seen · 44 lines · 28 tokens per session scan A 5d487d0834f5
stable-scope-effort-estimation is a skill published in the GitHub repository alonf/specrew (55 stars, last pushed yesterday), licensed MIT. It adds 28 tokens to every session and 958 once invoked, about $0.0001 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 2026-09-03.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…