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 agents/nearform/lastlight/triage-labelsgit clone --depth 1 https://github.com/nearform/lastlightWrote 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/agents/nearform/lastlight/triage-labels)<a href="https://agentmods.dev/agents/nearform/lastlight/triage-labels"><img src="https://agentmods.dev/badge/agents/nearform/lastlight/triage-labels.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 | $0.00000 | $0.01044 |
| Opus 5 | $0.00000 | $0.00522 |
| Sonnet 5 | $0.00000 | $0.00209 |
| Haiku 4.5 | $0.00000 | $0.00104 |
Grade A, and why
triage-labels 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 — 40 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Triage Labels
The skills speak in terms of five canonical triage roles. This file maps those roles to the actual label strings used in this repo's issue tracker.
| Label in mattpocock/skills | Label in our tracker | Meaning |
|---|---|---|
needs-triage |
needs-triage |
Maintainer needs to evaluate this issue |
needs-info |
needs-info |
Waiting on reporter for more information. A reporter (or maintainer) reply re-opens triage automatically (router-driven), provided no build has started yet. |
ready-for-agent |
ready-for-agent |
Fully specified, ready for an AFK agent |
ready-for-human |
ready-for-human |
Requires human implementation |
wontfix |
wontfix |
Will not be actioned |
When a skill mentions a role (e.g. "apply the AFK-ready triage label"), use the corresponding label string from this table.
Edit the right-hand column to match whatever vocabulary you actually use.
Labels Last Light writes and reads
Three more labels are part of the harness's own vocabulary rather than the triage roles above. The strings live in apps/server/src/cron/dependabot-discovery.ts, which is the single source of truth for them, and apps/server/tests/cron/label-vocab.test.ts pins them against the prompts that create them.
| Label | Who applies it | Who reads it | Meaning |
|---|---|---|---|
lastlight-ignore |
a human, only | the dispatch gate + the router | The hold. "Last Light, stay off this." Blocks every workflow on the issue or PR carrying it — triage, review, fix, merge, everything — and outranks an explicit @last-light … request, which gets one reply naming the label. Remove it and the bot resumes; nothing is persisted either way. Operator-configurable as hold.label (env LASTLIGHT_HOLD_LABEL); colour 24292f. |
requires-human |
the bot (escalation, and the agent per the dependabot prompts) | nothing — but its removal is read | A notification: "I stopped and a human should look." It holds nothing, and its presence is not a decision input. Taking it off is one: the bot reads "we escalated at this head, the head has not moved, our label is gone" as a maintainer asking for another try, and starts a fresh attempt-and-cost window at the same commit. So you never have to remove it — a push re-arms the loop with the label still on the PR — but removing it is one of the three ways to say "go again", alongside a push and @last-light retry [reason]. |
dependency-trivial / dependency-functional / dependency-major-{low,medium,high} |
the dependabot-pr-merge agent |
the merge prompt | The dependency-PR verdict + major-bump impact tier. See apps/server/spec/05-router.md. |
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 · 40 lines · 0 tokens per session scan A 72ce5802aa85
triage-labels is an agent published in the GitHub repository nearform/lastlight (22 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,044 tokens. 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 agents, from other repositories
code-reviewer
Dedicated code reviewer. Reads diffs/commits, reviews changed files, and returns a terse report of problems found. Prompt MUST specify scope: unstaged changes, a commit range, or since-branch-point. Read-only — no file edits.
vision
Analyze images with task-aware visual reasoning.
ss-reviewer
Independent code reviewer for the specship review stage — one member of the opt-in review panel. Use to get fresh, context-free eyes on a working diff, optionally through a named lens (correctness, security, performance, contract-consistency). Reports findings only; it does not fix code, decide the verdict, or touch…
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
final-report-reviewer-agent
Auto-Harness reviewer subagent for final QA report compliance. Use only immediately after evaluatorfinal writes the final QA report.
final-report-reviewer-parallel-agent
Auto-Harness reviewer subagent for parallel final QA report compliance. Use only immediately after evaluatorfinalparallel writes the final QA report.