Borrowing it
Nothing to install: this file belongs to mikuare/Code-Ledger. 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/mikuare/Code-Ledger/main/.claude/skills/scope-check/SKILL.mdgit clone --depth 1 https://github.com/mikuare/Code-LedgerWrote 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/mikuare/code-ledger/scope-check)<a href="https://agentmods.dev/skills/mikuare/code-ledger/scope-check"><img src="https://agentmods.dev/badge/skills/mikuare/code-ledger/scope-check/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/mikuare/code-ledger/scope-check"><img src="https://agentmods.dev/badge/skills/mikuare/code-ledger/scope-check.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 | $0.00085 | $0.01113 |
| Opus 5 | $0.00043 | $0.00557 |
| Sonnet 5 | $0.00017 | $0.00223 |
| Haiku 4.5 | $0.00009 | $0.00111 |
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 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.
How it starts
The opening of the file, as written. The whole thing — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Scope check
A correct fix wrapped in unrelated churn is still a bad diff: harder to review,
destructive to git blame, and far more likely to collide with another agent's
in-flight work. This audits an existing diff and removes only the churn.
Two passes. The first is deterministic and comes from the index; the second is git. Do both — they catch different things.
This file is guidance, not enforcement
Nothing here blocks anything. The deterministic answer lives in CodeLedger and is the same whether or not an agent read this file; these steps just make sure somebody asks for it.
Pass 1 — what the index can prove
Declare the scope before the work if you can (codeledger task --scope <paths|symbols>),
then ask:
codeledger scope "<the task>" # add --json for the machine-readable form
| Verdict | Meaning |
|---|---|
CLEAN |
every recorded change is code, inside scope |
TEXT_ONLY |
bytes moved in a file and no symbol moved with them — formatting or comment churn |
OUT_OF_SCOPE |
code changed that the declared scope does not cover |
UNKNOWN |
containment could not be proven — not a pass; the reasons are listed |
A declared scope is exact: auth.py::authenticate does not authorize editing
auth.py::helper; declaring auth.py does. affected_scope is what the change
reaches downstream — being affected is never a licence to have edited it, and a
claim is editing authority, not evidence that a change belonged to the task.
If nothing is recorded yet, record it first:
codeledger refresh --changed --agent <you> --request "<the task>"
Its effect is the aggregate view — symbols-changed, text-only, none —
and scope.status is the older boundary check. codeledger scope is the
per-file, per-symbol answer and is what to trust when they disagree in detail.
Pass 2 — what git can prove
git status --short
git diff --stat
# Files whose entire change is whitespace and blank lines:
for f in $(git diff --name-only); do
[ -z "$(git diff -w --ignore-blank-lines -- "$f")" ] && echo "FORMATTING ONLY: $f"
done
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 · 114 lines · 85 tokens per session scan A fa65f0a5bc36
scope-check is a skill published in the GitHub repository mikuare/Code-Ledger (0 stars, last pushed 4d ago), licensed MIT. It adds 85 tokens to every session and 1,113 once invoked, about $0.0004 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 2026-09-09.
Other skills, from other repositories
review-implement-phase
Implements triaged review actions, commits focused fixes, and posts Done plus resolves threads. Use when the user wants only the implementation phase of the review-framework workflow.
engram-branch-pr
PR creation workflow for Engram following the issue-first enforcement system. Trigger: When creating a pull request, opening a PR, or preparing changes for review.
verify-behavior
Verify or reproduce visible product behavior by driving the real UI with pi-computer-use's checked tools, requiring verified expect postconditions and durable state evidence for meaningful UI flows. Use when triage needs visual reproduction, implementation needs behavioral proof, review needs interactive confirmation…
github-contributor
End-to-end playbook for shipping high-quality pull requests to open-source projects you don't maintain — discovery, CONTRIBUTING compliance, PR-size check, minimal-diff implementation, PR description with AI-assisted disclosure, conflict resolution, and post-submission maintainer interaction. Use whenever creating…
revdiff
Review diffs, files, and documents with inline annotations in a TUI overlay, or answer questions about revdiff usage, configuration, themes, and keybindings. Opens revdiff in agterm/tmux/zellij/herdr/kitty/wezterm/cmux/ghostty/iterm2/emacs-vterm, captures annotations, and addresses them. Works in git, hg, and jj repos…
oss-maintainer
Run an open-source project's issue/PR/release loop like a careful human maintainer — triage to root cause, absorb community PRs before duplicating them, gate every merge, ship honest releases, and thank the people doing your QA for free.