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/nearform/lastlight/lastlight-debugnpx skills add nearform/lastlight --skill lastlight-debuggit clone --depth 1 https://github.com/nearform/lastlightWhat 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 | $0.00138 | $0.01637 |
| Opus 5 | $0.00069 | $0.00818 |
| Sonnet 5 | $0.00028 | $0.00327 |
| Haiku 4.5 | $0.00014 | $0.00164 |
Grade A, and why
lastlight-debug 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 3d 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 — 150 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Debug a Last Light instance via the CLI
Read a running instance's state over its admin API with the lastlight CLI — no
SSH, no poking SQLite or jsonl files on the box. Every command takes --json
for machine-parseable output; prefer it when you need to extract fields.
This is the operator counterpart to lastlight-client (which logs the CLI
in). If lastlight status errors with no saved config, run lastlight-client
first.
1. Connect
The CLI talks to whatever instance you logged into (saved in
~/.lastlight/config.json). Confirm you're pointed at the right one and the
token is valid:
lastlight status # instance URL, server health, token validity
If the token is missing/expired, log in (lastlight login https://<instance>,
or --password for headless) — that's the lastlight-client flow. For
one-off targeting without saving, pass --url / --token on any command, or
set LASTLIGHT_URL / LASTLIGHT_TOKEN (env wins over the saved config).
2. Find the broken run
lastlight workflow list --status failed # recent failures
lastlight workflow list --status active # running + paused now
lastlight workflow list --workflow pr-review --limit 50
Copy the run ID from the table. The PHASE column names the phase the run is
at (or failed on).
3. Inspect the run's phases
lastlight workflow log <run-id> # run header + per-phase table (✓/✗/…, duration, session id, error)
lastlight workflow log <run-id> --follow # then tail the current phase live
The phase table shows which phase failed, its error snippet, and the SESSION
id you need for the transcript. A phase stuck at … never finished (still
started); a ✗ finished failed.
If it failed on a transient/infra hiccup, re-run from the failed phase:
lastlight workflow retry <run-id> # resumes from the phase that failed (same workspace/context)
Not the same thing as pr retry. workflow retry resumes one FAILED run.
When the bot correctly gave up on a pull request — requires-human applied,
one comment explaining what it tried, no failed run to resume — the budgets are
what stand in the way, and moving them is pr retry:
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.
- 3d ago First seen · 150 lines · 138 tokens per session scan A 84bae860139d
lastlight-debug is a skill published in the GitHub repository nearform/lastlight (22 stars, last pushed 6d ago), licensed MIT. It adds 138 tokens to every session and 1,637 once invoked, about $0.0007 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
example-skill
Counts lines, words, and bytes in a text file using the bundled count.sh script. Use when asked to count/measure a file's size in these terms.
design-taste-frontend
Anti-slop frontend skill for landing pages, portfolios, and redesigns. The agent reads the brief, infers the right design direction, and ships interfaces that do not look templated. Real design systems when applicable, audit-first on redesigns, strict pre-flight check.
open-code-review
Performs AI-powered code review on Git changes using the ocr CLI from alibaba/open-code-review. Use when the user asks to review code, review a pull request, review staged/unstaged changes, review a commit, or compare branches for code quality issues. Produces line-level review comments and can automatically apply…
image-to-code
Elite website image-to-code skill for Codex. For visually important web tasks, it must first generate the design image(s) itself, deeply analyze them, then implement the website to match them as closely as possible. In Codex, it must prefer large, readable, section-specific images instead of tiny compressed boards…
imagegen-frontend-mobile
Elite mobile app image-generation skill for creating premium, app-native screen concepts and flows. Designed for iOS, Android, and cross-platform mobile products. Prioritizes clean hierarchy, comfortably readable text, strong multi-screen consistency, controlled color palettes, non-generic creative direction, textured…
design-taste-frontend-v1
The original v1 taste-skill, preserved for projects depending on its exact behavior. The current default is design-taste-frontend (v2 experimental), which is a substantial rewrite. Use this v1 install name only if you need exact backward compatibility.