Borrowing it
Nothing to install: this file belongs to auerbachb/claude-code-config. 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/auerbachb/claude-code-config/main/.claude/skills/pause/SKILL.mdgit clone --depth 1 https://github.com/auerbachb/claude-code-configWrote 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/auerbachb/claude-code-config/pause)<a href="https://agentmods.dev/skills/auerbachb/claude-code-config/pause"><img src="https://agentmods.dev/badge/skills/auerbachb/claude-code-config/pause/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/auerbachb/claude-code-config/pause"><img src="https://agentmods.dev/badge/skills/auerbachb/claude-code-config/pause.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 | $0.00073 | $0.14861 |
| Opus 5.5 | $0.00029 | $0.05944 |
| Sonnet 5.5 | $0.00015 | $0.02972 |
| Haiku 4.5 | $0.00007 | $0.01486 |
Grade B, and why
pause scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 22d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
chmod 644 "$MARKER_PATH" How it starts
The opening of the file, as written. The whole thing — 884 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Land what can land. Park the rest at a deliberate boundary. Write a resume point you can pick up cold.
Two outputs, in this order: an active wind-down that drives near-done PRs to merged, then a machine-readable marker and human-readable summary the companion /pause-resume reads when you sit back down.
This command never relaxes a gate. cr-merge-gate.md Steps 1–1d, 1b and the Step 2 AC verification bind unchanged. The hard stops in CLAUDE.md "PR MERGE AUTHORIZATION" (human CHANGES_REQUESTED on HEAD, failing/incomplete CI, unresolved threads, unchecked AC, protection-modifying bypass) are hard stops here. The window never makes a borderline PR eligible; it only decides how long to wait on already-eligible ones.
One parameter: the runway, /pause [N]. /pause 5 gives a five-minute
runway, /pause 0 stops immediately, and plain /pause uses the fifteen-minute
default graceful shutdown runway and triage threshold. --window Nm is the
equivalent long form (/pause 5 = /pause --window 5m); a caller may choose a
shorter or longer non-negative window either way. The command stops earlier when all owned work is terminal.
At the chosen deadline it stops leftovers; it never merely returns while
billable work continues.
The window is a ceiling on the whole run, not a budget for its middle. It
bounds every phase — landing, park bookkeeping, marker writing, state
persistence — and not merely the land phase. Once the deadline passes, the run
stops all remaining non-terminal work and cuts straight to the bounded terminal
path defined in Step 0, degrading optional output rather than blowing the
ceiling. A /pause 15 (--window 15m) is observably finished shortly after minute
15, every time, and Step 8 names what was skipped to make that true.
Step 0: Resolve helpers and parse arguments
/pause is invocable from any thread — including one whose cwd is not this repo. Resolve each helper the same way every other stop-style command does:
# Command entry — stamp the clock FIRST. The window is measured from the moment
# /pause was invoked, so preflight (resolving helpers, discovering the repo,
# reading the shutdown reference) is spent inside the window, not free time
# before it. Starting the clock after preflight would silently extend every
# deadline and under-report elapsed time in Step 8.
T_START=$(date -u +%s)
resolve_script() {
local name="$1" candidate
for candidate in \
"$HOME/.claude/skills-worktree/.claude/scripts/$name" \
"$HOME/.claude/scripts/$name"; do
if [[ -x "$candidate" ]]; then echo "$candidate"; return 0; fi
done
return 1
}
SESSION_STATE_SH=$(resolve_script session-state.sh) || SESSION_STATE_SH=""
HANDOFF_STATE_SH=$(resolve_script handoff-state.sh) || HANDOFF_STATE_SH=""
MERGE_GATE_SH=$(resolve_script merge-gate.sh) || MERGE_GATE_SH=""
AC_CHECKBOXES_SH=$(resolve_script ac-checkboxes.sh) || AC_CHECKBOXES_SH=""
PR_STATE_SH=$(resolve_script pr-state.sh) || PR_STATE_SH=""
LOCAL_REVIEW_SH=$(resolve_script local-review.sh) || LOCAL_REVIEW_SH=""
CLEAN_BEHIND_SH=$(resolve_script clean-behind-check.sh) || CLEAN_BEHIND_SH=""
TABLE_FRESHNESS_SH=$(resolve_script table-freshness.sh) || TABLE_FRESHNESS_SH=""
EXECUTION_PAUSE_SH=$(resolve_script execution-pause.sh) || EXECUTION_PAUSE_SH=""
TASK_REGISTRY_SH=$(resolve_script background-task-registry.sh) || TASK_REGISTRY_SH=""
# Resolve repository identity independently of session-state persistence so a
# degraded state helper does not make the recovery marker undiscoverable.
REPO_KEY=""
if [[ -n "$SESSION_STATE_SH" ]]; then
REPO_KEY=$("$SESSION_STATE_SH" --repo-key 2>/dev/null) || REPO_KEY=""
# `--repo-key` NEVER returns empty: it prints `_unknown` and exits 0 when it
# cannot resolve a repo. Normalise that sentinel to empty so the fallback
# below actually runs and the `-z` guards downstream actually fire —
# otherwise teardown clears `_unknown`, a scope nothing polls, and reads as a
# successful disarm while the live record keeps the floor armed.
[[ "$REPO_KEY" == "_unknown" ]] && REPO_KEY=""
fi
if [[ -z "$REPO_KEY" ]]; then
REMOTE=$(git remote get-url origin 2>/dev/null) || REMOTE=""
REPO_KEY=$(printf '%s' "$REMOTE" | sed -e 's|\.git$||' \
-e 's|.*github\.com[:/]\([^/]*/[^/]*\)$|\1|')
[[ "$REPO_KEY" =~ ^[A-Za-z0-9._-]+/[A-Za-z0-9._-]+$ ]] || REPO_KEY=""
REPO_KEY=$(printf '%s' "$REPO_KEY" | tr '[:upper:]' '[:lower:]')
fi
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.
- 22d ago Changed · +13 lines 6248494f8eaf
- 1mo ago Changed 48dfdabcf630
- 1mo ago Changed · +434 lines 1007a8deb0f4
- 2mo ago First seen · 437 lines · 73 tokens per session scan B 205c1d1263f7
pause is a skill published in the GitHub repository auerbachb/claude-code-config (5 stars, last pushed 2d ago), licensed MIT. It adds 73 tokens to every session and 14,861 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
Review Comment Triage (No-Code-Fix Mode)
A review workflow for sorting existing pull-request comments by severity, status, and next action without changing the code.
OpenSourceManagement
Triages open issues, pull requests and GitHub Discussions across the principal's own open-source repos (the list in Config.md) via the gh CLI, ranks what needs attention with suggested replies, posts edit-in-place marker comments, diffs new Ollama library models against a local model box, and takes a private repo…
recipe-front-review
Reviews completed frontend implementation for governing-source compliance, scope economy, repository quality, and security, then applies user-approved React corrections.
referee
Final arbiter for Bug Hunter. Independently verifies behavioral findings, resolves Skeptic challenges, and calibrates severity and confidence.
output-eval-error-analysis
Systematically review workflow traces to identify failure modes before building evaluators. Use when starting an eval project, after significant pipeline changes, or when production quality drops.
idea-team
A structured group discussion for exploring a product idea through three roles: researcher, critic, and analogy finder. The roles look for evidence, weaknesses, and useful comparisons.