Runs ready tickets in parallel through Claude Code workers, then gates and merges the results.
Flail Detector
adlc · Agent
Flail detector watches the session log of a build agent for signs that it is going round in circles. It applies a mechanical two-strike rule across five signals: the same error repeating, files written outside a declared scope, the same file edited again and again, a log past a size limit, and token spend over a ticket's budget. On a trigger it prints a recommendation and exits with code 2, and it accepts plain-text or JSONL logs without making any model calls.
Written by ooruby from the README of @adlc/flail-detector 1.12.0.
Not claimed by its maker. Is this yours? Prove it and answer the findings
Why it's useful
It spots an agent going in circles from its own log using fixed rules, so no extra model call is needed to notice.
What you could do with it
- Point it at a session log with a scope pattern to see whether the agent wrote to files outside the ticket's scope.
- Set how many times an error may repeat in the log before the check fails.
- Pass the tokens spent and the ticket's budget so the check fails when spend goes over it.
Written from its documentation: what it says it can do, not what our checks found.
Maintenance
Not measuredNo release date is on record for this package yet. The nightly publisher check records one as it reaches each npm package, about once every ten nights.
Release activity only: it says nothing about quality or safety, and a finished small package can be fine without releases. How it is measured
What this does not cover
- Everything. Treat it as you would software from anywhere else.
Receipt history: every signed receipt for every version of this listing, and what changed between them.
In its maker's words
Session-log flail analysis — mechanical two-strike rule for build agents (C6/P4 supervisor).
Compare with
Compare all 4How far this has been checked
Static scanned
- What it establishes
- Its published package, or for a hosted server its source repository at a recorded commit, was read file by file, without running it, by every check in our current scan.
- What it does not
- How it behaves when it runs, or anything the scan does not read yet: several rubric checks, the repository's history, and compiled code in folders named dist or build. For a hosted server, that the endpoint runs the code that was read. The ooruby Index sets out exactly what was read.
- Exactly what was read
- Version 1.12.0, the file with digest sha512-8amZpmiYKCUpLsi09Py93fYdJHwgMHPXKMWS/8UlP9Fv/MiN5Hjg5OPx0xtqLZhlEt4UwY5hfN7yIST4s/b9RA==, as the registry publishes it. A published version cannot be replaced, so this names the same bytes for anyone who checks.
- Authentication
- Runs locally. No hosted endpoint is listed for this package. You run it on your own machine, so there is no endpoint of ours to authenticate against.
Adding it
Run it with:
npx -y @adlc/flail-detector@1.12.0Pinned to 1.12.0, which is the version the findings above were found in. Drop the version to take whatever is newest, and the report on this page stops describing what you installed.
Where this came from
- Registry
- npm
- Package
- @adlc/flail-detector
- Version read
- 1.12.0
- Resolved
- 2026-10-10
Built from source, attested
npm publishes a signed statement that this exact package was built from the repository below, at this commit. It is verifiable without taking our word for it.
- Repository
- github.com/voodootikigod/adlc
- Commit
- bddae80871bf
- Built by
- github.com/actions/runner/github-hosted
- Registry publish attestation
- signed by npm · 2026-10-10
- Checked
- 2026-10-10
The badge, if this is your listing
It renders the current rung (static scanned) and links back here, where what that does and does not establish is one click away. It updates itself as the evidence deepens.
[](https://ooruby.com/market/adlc-flail-detector)About this listing
- Kind
- Agent
- Category
- Developer tools
- Pricing
- Free
- Sandbox
- No
- Hosted
- No
- Updated
- 2026-10-10
More from adlc
See the storefrontChecks that a ticket is self-contained before a build agent starts, by asking a model what is missing.
Predicts which parallel tickets would collide on merge before any agent runs, and orders the merges.
Similar agents
All agentsVerification records what our published tests found on a specific version at a specific date. It is not a warranty, and it does not certify that software is free of defects.