anarlog is a local-first AI meeting notetaker that captures device audio, transcribes meetings, and stores notes, transcripts, and recordings on the user's computer. It is for people who want meeting notes without adding a bot to calls or sending conversation data to an external cloud. The catalogue entries provide agent integrations and workflows for the application.
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 agentmods add skills/fastrepl/anarlog/fix-ready-prsnpx skills add fastrepl/anarlog --skill fix-ready-prsgit clone --depth 1 https://github.com/fastrepl/anarlogWrote 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/fastrepl/anarlog/fix-ready-prs)<a href="https://agentmods.dev/skills/fastrepl/anarlog/fix-ready-prs"><img src="https://agentmods.dev/badge/skills/fastrepl/anarlog/fix-ready-prs.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 | $0.00055 | $0.01303 |
| Opus 5 | $0.00028 | $0.00651 |
| Sonnet 5 | $0.00011 | $0.00261 |
| Haiku 4.5 | $0.00006 | $0.00130 |
Grade A, and why
fix-ready-prs 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 5d 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 — 171 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Fix Ready PRs
Work through every open, non-draft pull request. Fix CI failures and unresolved Bugbot findings on the existing PR branch. Do not open a new PR for an existing one.
Drafts are out of scope unless the user names them.
1. Inventory
gh pr list --state open --limit 200 \
--json number,title,isDraft,headRefName,headRepositoryOwner,isCrossRepository,url,mergeStateStatus
Keep only isDraft == false. Record number, branch, URL, and whether the head
is a fork (isCrossRepository).
2. Collect failures
For each ready PR, gather current-head CI and unresolved Bugbot threads. Do not treat an in-progress check as green.
CI
gh pr checks <n>
gh pr view <n> --json statusCheckRollup,headRefOid
Treat as a failure when a required or repo workflow check is FAILURE,
TIMED_OUT, ACTION_REQUIRED, or CANCELLED on the current head and has not
been superseded by a newer run.
Ignore:
SKIPPED/NEUTRAL- Netlify header/pages/redirect checks and canceled deploy previews
- Mintlify Deployment skips
- macOS/Windows/iOS jobs that this repo skips on pull requests
If a failing job has logs, pull them:
gh run view <run-id> --log-failed
If checks are still IN_PROGRESS / pending, wait until they finish or fail
before declaring the PR clean. Re-poll rather than guessing.
Bugbot
Use review threads, not only the Bugbot check conclusion. A green Bugbot check can still leave unresolved comments, and an older finding may already be fixed.
GitHub returns reviewThreads oldest-first with no unresolved-only filter.
Page until hasNextPage is false. Do not stop at the first 50 threads.
after=""
while :; do
if [ -n "$after" ]; then
page=$(gh api graphql -f query="$THREADS_QUERY" -F n=<n> -F after="$after")
else
page=$(gh api graphql -f query="$THREADS_QUERY" -F n=<n>)
fi
echo "$page" | jq '.data.repository.pullRequest.reviewThreads.nodes[]'
has_next=$(echo "$page" | jq -r '.data.repository.pullRequest.reviewThreads.pageInfo.hasNextPage')
after=$(echo "$page" | jq -r '.data.repository.pullRequest.reviewThreads.pageInfo.endCursor')
[ "$has_next" = true ] || break
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.
- 5d ago First seen · 171 lines · 55 tokens per session scan A e399a25cf8fb
fix-ready-prs is a skill published in the GitHub repository fastrepl/anarlog (9,234 stars, last pushed yesterday), licensed MIT. It adds 55 tokens to every session and 1,303 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
shellx-host
ShellX host-session manifest. Use only when the current prompt or runtime metadata positively identifies this session as running inside ShellX, when ShellX host tools are advertised, or when the user explicitly asks about ShellX host APIs or surfaces. Do not use merely because this skill is installed, a project…
design-language
Use when building, modifying, or fixing any frontend UI in the Asyar launcher — new components, new views, layout changes, styling decisions, new built-in features, visual bug fixes, and anything in settings or onboarding. Answers "what do I use here?" for fonts, colour, typography, spacing, motion, components, and…
architectural-integrity
Use before planning or implementing ANY feature, bug fix, refactor, or API change that touches Asyar's architecture — extension system, service layer, IPC contracts, Tauri commands, manifest contributions, or cross-layer data flow. Triggers on new features, new extension APIs, new services, bug fixes involving…
generated-files
Never hand-edit or hand-copy generated content. Use when touching permissions.rs, error.rs, AppError/SearchError variants, runtimes/catalog.fallback.json, any #[derive(specta::Type)] struct, any file with an AUTO-GENERATED banner (kinds.ts, gatedPermissions.ts, knownRuntimes.ts, bindings.ts, emoji data), or whenever…
dev-environment
Reference for the Asyar monorepo structure, SDK workspace linking, lockfile discipline, CI workflows, and release flow. Use this skill whenever working on anything related to pnpm workspace setup, the asyar-sdk dependency, lockfile errors, SDK or launcher version bumps, CI configuration, release workflow, or questions…
review-ipc
Audit IPC message contracts between extensions and the Asyar host. Use when adding a new SDK service, adding a new proxy method, changing a postMessage type string, or reviewing permission gate coverage.