lastlight-debug

A troubleshooting guide for a running Last Light server, using the Last Light command-line client to inspect workflows and logs through the server's admin interface.

In plain words
What is it for?
Check server health, list active or failed workflows, inspect run details, search logs, and investigate why an automated task did not complete.
Why use it?
It helps find failed, paused, or stuck agent runs without logging in to the server host or reading its internal files directly.

Skill for Claude CodeCodex

Part of the lastlight plugin — 7 skills shipped together

Install

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.

agentmods
npx agentmods add skills/nearform/lastlight/lastlight-debug
Any agent
npx skills add nearform/lastlight --skill lastlight-debug
Clone the repo
git clone --depth 1 https://github.com/nearform/lastlight

Made for: Claude Code, Codex.

Or install lastlight, the plugin that ships this one along with the rest of its 7 skills.

Per session 138 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,637 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 3d ago against content hash 84bae860139d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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.

plugins/lastlight/skills/lastlight-debug/SKILL.md · 150 lines

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:

Read the full file on GitHub · 150 lines

Changes

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.

  1. 3d ago First seen · 150 lines · 138 tokens per session scan A 84bae860139d

Subscribe to this mod's changes

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.

Related

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.

sammwyy/clay · 37 tokens

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.

Leonxlnx/taste-skill · 61 tokens

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…

alibaba/open-code-review · 98 tokens

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…

Leonxlnx/taste-skill · 116 tokens

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…

Leonxlnx/taste-skill · 126 tokens

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.

Leonxlnx/taste-skill · 61 tokens