Borrowing it
Nothing to install: this file belongs to neoneye/agent-memory-atlas. 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/neoneye/agent-memory-atlas/main/.agents/skills/work-the-queue/SKILL.mdgit clone --depth 1 https://github.com/neoneye/agent-memory-atlasWrote 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/neoneye/agent-memory-atlas/work-the-queue)<a href="https://agentmods.dev/skills/neoneye/agent-memory-atlas/work-the-queue"><img src="https://agentmods.dev/badge/skills/neoneye/agent-memory-atlas/work-the-queue/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/neoneye/agent-memory-atlas/work-the-queue"><img src="https://agentmods.dev/badge/skills/neoneye/agent-memory-atlas/work-the-queue.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 | $0.00080 | $0.01731 |
| Opus 5.5 | $0.00032 | $0.00692 |
| Sonnet 5.5 | $0.00016 | $0.00346 |
| Haiku 4.5 | $0.00008 | $0.00173 |
Grade A, and why
work-the-queue 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 1mo 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 — 170 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Work the Queue
One item, start to finish. This skill does not decide what to read — that is
scripts/queue.py's job, and the reasoning behind its ranking is in
notes/2026-08-04-automating-re-analysis.md. This skill takes what the queue
hands over and finishes it, which means the reading, the integration, the build,
the commit, the push, and only then the removal.
The queue is not a plan and not a promise. It holds at most five links and
lives in gitignored scripts/state/queue.txt. Anything in it can be wrong, out
of date, or a bad idea on inspection — see "When to put it back" below.
Take one item
python3 scripts/queue.py peek # bare URL of the top item
python3 scripts/queue.py list # the whole queue with the reasons for each pick
peek exits 1 on an empty queue. Fill it and look at what came back:
python3 scripts/queue.py fill
If fill warns that the register is old, stop and rebuild it rather than
working a stale pick — the item may already be done.
GITHUB_TOKEN=... python3 scripts/drift_report.py --out scripts/state/drift.jsonl
Read the reason on the line you are about to work. It carries the status, the drift, the star count, the last reading and the score, and it is there so the pick can be argued with. If the reason does not justify the work, say so and take the next one — the ranking is a heuristic, not an instruction.
Decide which skill this is
rg -l -i "^source_url: .*${OWNER}/${REPO}\b" content/systems/
- A report exists →
reanalyze-memory-system. Re-pinning, deciding whether a published claim went stale, re-running every absence search, and the rename-and-redirect convention all live there. - No report →
add-memory-system. Scaffolding, the capability definitions, the matrix rules and the integration checklist live there.
Check for a rename before concluding there is no report: a project that renamed
itself may be in the atlas under its old name, and GitHub redirects the API but
not your grep. Grep the atlas for the old name and the changelog for renamed.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 1mo ago Changed 5af2dfff4a8f
- 1mo ago First seen · 170 lines · 80 tokens per session scan A b858522b7108
work-the-queue is a skill published in the GitHub repository neoneye/agent-memory-atlas (104 stars, last pushed today), licensed MIT. It adds 80 tokens to every session and 1,731 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-09-10.
Other skills, from other repositories
commitlore-commits
Use when about to make a git commit and there is decision context worth recording — a constraint that shaped the change, an alternative that was tried and dropped, a warning for whoever touches this next. Drives the CommitLore capture pipeline, which drafts a record from the session transcript and the staged diff…
commitlore-setup
Use when a git repository needs CommitLore wired up for the first time, or when its hook/notes configuration looks broken. Runs the diagnostic, installs the commit-msg validation hook, fixes the notes fetch refspec so records survive a clone or fetch, and builds the local record index. Trigger phrases include "set up…
commitlore-commits
Capture a decision record from verified session and diff evidence before a commit.
fix-pr-commit-titles
Bulk-rewrite commit titles on a PR branch to match [LKPR-N] format using filter-branch — avoids per-commit hook re-runs.
github-pr-workflow
GitHub PR lifecycle: branch, commit, open, CI, merge.
proposal-filing
File a new Lorekeeper proposal ticket — create markdown, create GitHub issue, commit, push. Use when requesting a new feature, filing a bug, or submitting a product idea.