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/pr-monitor-and-manage-wake/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/pr-monitor-and-manage-wake)<a href="https://agentmods.dev/skills/auerbachb/claude-code-config/pr-monitor-and-manage-wake"><img src="https://agentmods.dev/badge/skills/auerbachb/claude-code-config/pr-monitor-and-manage-wake/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/pr-monitor-and-manage-wake"><img src="https://agentmods.dev/badge/skills/auerbachb/claude-code-config/pr-monitor-and-manage-wake.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Prompt Injection · line 137 Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.
- high Prompt Injection · line 137 Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.
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 | $0.04581 |
| Opus 5 | $0.00043 | $0.02291 |
| Sonnet 5 | $0.00017 | $0.00916 |
| Haiku 4.5 | $0.00009 | $0.00458 |
Grade A, and why
pr-monitor-and-manage-wake 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 6d 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 — 293 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Resume companion to /pr-monitor-and-manage. Wakes a paused PR-fleet manager: reads the pause marker, stops any auto-wake Monitor, clears the marker, and re-arms the main Monitor at base cadence.
Idempotent: running on a non-paused session is a clean no-op.
Post-merge symlink: after merge to
main, symlink~/.claude/skills/pr-monitor-and-manage-wake→~/.claude/skills-worktree/.claude/skills/pr-monitor-and-manage-wakeperskill-symlinks.md— never copy, never symlink to the root repo.
Resolve the state helper
Same three-candidate lookup as /babysit-pr-stop:
resolve_script() {
local name="$1" candidate
for candidate in \
"$HOME/.claude/skills-worktree/.claude/scripts/$name" \
"$HOME/.claude/scripts/$name" \
".claude/scripts/$name"; do
if [[ -x "$candidate" ]]; then echo "$candidate"; return 0; fi
done
return 1
}
SESSION_STATE_SH=$(resolve_script session-state.sh) || { echo "ERROR: session-state.sh not found" >&2; exit 1; }
Step 1: Parse mode
--auto-check— lightweight fleet scan (invoked by the auto-wake Monitor). Comparegh pr listagainst.pmm.fleet_at_pause; re-launch main skill only if changed. It must carry the runtime-only--monitor-generation <token>emitted by that Monitor.- No flags (default) — user-initiated resume: clear marker, stop the re-scan, re-arm the main Monitor.
Before reading the pause marker in --auto-check mode, parse the supplied generation and compare it
with .pmm.auto_wake_monitor_generation. Missing or unequal means a queued event from an old or
unidentified re-scan: print [auto-check] Ignoring a stale Monitor generation. and exit 0 without
reading GitHub or mutating state. This gate is first so an event queued before exact TaskStop
cannot see a later pause marker and cancel or resume the replacement generation.
Execute that parser and generation gate explicitly before Step 2:
MODE="user-resume"
AUTO_CHECK_GENERATION=""
_AUTO_CHECK_EXPECT_GENERATION=false
for _WAKE_ARG in $ARGUMENTS; do
if [[ "$_AUTO_CHECK_EXPECT_GENERATION" == true ]]; then
AUTO_CHECK_GENERATION="$_WAKE_ARG"
_AUTO_CHECK_EXPECT_GENERATION=false
continue
fi
case "$_WAKE_ARG" in
--auto-check) MODE="auto-check" ;;
--monitor-generation) _AUTO_CHECK_EXPECT_GENERATION=true ;;
esac
done
if [[ "$_AUTO_CHECK_EXPECT_GENERATION" == true ]]; then
echo "ERROR: --monitor-generation requires a token." >&2
exit 2
fi
if [[ "$MODE" == "auto-check" ]]; then
RECORDED_AUTO_CHECK_GENERATION=$("$SESSION_STATE_SH" --get '.pmm.auto_wake_monitor_generation' 2>/dev/null || echo null)
if [[ -z "$AUTO_CHECK_GENERATION" || "$AUTO_CHECK_GENERATION" == "null" ||
"$AUTO_CHECK_GENERATION" != "$RECORDED_AUTO_CHECK_GENERATION" ]]; then
echo "[auto-check] Ignoring a stale Monitor generation."
exit 0
fi
elif [[ -n "$AUTO_CHECK_GENERATION" ]]; then
echo "ERROR: --monitor-generation is runtime-only and requires --auto-check." >&2
exit 2
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.
- 6d ago Changed · +20 lines 5d209cad5e6f
- 12d ago First seen · 273 lines · 85 tokens per session scan A ad566e8a8bdf
pr-monitor-and-manage-wake is a skill published in the GitHub repository auerbachb/claude-code-config (5 stars, last pushed today), licensed MIT. It adds 85 tokens to every session and 4,581 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 2026-08-31.
Other skills, from other repositories
robin
Use whenever an agent creates, updates, reviews, or completes a GitHub pull request. Detect whether Robin is installed in the repository; when it is, automatically drive the PR through a bounded review, verified-fix, reply, thread-resolution, re-review, authorized-merge, and cleanup loop without requiring the user to…
hyperflow-audit
Hyperflow code review. Use when the user wants the current diff, a commit, branch, or PR reviewed — verbs like audit, review, "check for issues", "security check", "code review". Multi-level review (L1 quick → L5 exhaustive), writes findings to .hyperflow/audits/, then a fix-gate.
phx-pr-review
Address feedback left on a GitHub pull request: fetch unresolved review threads, make agreed Elixir/Phoenix code fixes, reply, and resolve. Use for a PR URL/number or reviewer comments. NOT for pre-PR review, findings triage, or CI monitoring.
get-pr-reviews
Get nicely formatted output of the last review comments on a PR. Used internally by other skills.
no-mistakes
Validate committed feature-branch changes through the no-mistakes pipeline: intent, rebase, review, test, docs, lint, push, PR, and CI. Use when the user asks to run no-mistakes, ship safely, validate before pushing, or gate a change before it reaches upstream.
pr-threshold
Track commit accumulation and trigger PR when thresholds crossed.