Borrowing it
Nothing to install: this file belongs to mtarcure/claude-vibe-squad. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/mtarcure/claude-vibe-squad/main/.agents/skills/scope-estimation/SKILL.mdgit clone --depth 1 https://github.com/mtarcure/claude-vibe-squadWrote 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/mtarcure/claude-vibe-squad/scope-estimation)<a href="https://agentmods.dev/skills/mtarcure/claude-vibe-squad/scope-estimation"><img src="https://agentmods.dev/badge/skills/mtarcure/claude-vibe-squad/scope-estimation.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 5.1 | $0.00070 | $0.00404 |
| Opus 5 | $0.00035 | $0.00202 |
| Sonnet 5 | $0.00014 | $0.00081 |
| Haiku 4.5 | $0.00007 | $0.00040 |
Grade A, and why
scope-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 7d 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 Estimation
Measure the corpus before analyzing it, so the retrieval plan and the confidence claims are sized to what was actually read rather than to what was sampled.
Steps
- Count the corpus before opening it: number of files, total bytes, and the largest single file. An analysis plan written before this count is a guess.
- Convert size to a budget in the units that actually bind — context window, tool calls, and wall-clock — and state which one binds first.
- Classify the corpus into read-fully, sample, and index-only tiers. Record the rule used to assign each tier, not just the assignment.
- Declare the sampling fraction per tier as a number. "Reviewed the codebase" is not a scope statement; "read 34 of 210 files, all 9 entry points" is.
- Identify what the chosen tiers structurally cannot answer, and say so before the analysis rather than after a reader asks.
- Re-measure when the corpus grows mid-task. A scope claim inherited from an earlier, smaller corpus is stale and silently overstates coverage.
- Carry the final numbers into the deliverable so every conclusion inherits an explicit denominator.
Acceptance
- File count, total size, and largest-file size are stated as measured numbers.
- The binding budget is named, and the tier assignment rule is written down.
- Sampling fractions appear as counts with denominators, never as adjectives.
- The deliverable names at least one question the chosen scope cannot answer.
- No coverage claim exceeds the measured read set.
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.
- 7d ago First seen · 26 lines · 70 tokens per session scan A f3fb3fa295f4
scope-estimation is a skill published in the GitHub repository mtarcure/claude-vibe-squad (90 stars, last pushed 2d ago), licensed MIT. It adds 70 tokens to every session and 404 once invoked, about $0.0003 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
contributor-onboarding
Help a new contributor get productive on this checkout - inspect sync state against main, build, run the repository's exact verification gate, and produce a local what's-new digest. Never fetches, pulls, or modifies a dirty tree on its own. Explicit-only.
codew-release-qa-sweep
Use before claiming Codewhale release work is done: run the full gate sweep and list the manual QA targets.
gh-file-issue
Use when filing a new Codewhale GitHub issue: turn a bug or idea into a well-formed, actionable issue with repro, acceptance criteria, labels, and milestone.
gh-find-prs
Survey open Codewhale PRs and triage each for mergeability and disposition against the real landing branch.
gh-treasure-hunt
Hunt the issue/PR queue for highest value-over-risk wins: clean focused community PRs, already-implemented issues to close, safe quick-fixes.
rust-check
Run cargo check on the current Rust project to find compile errors.