Borrowing it
Nothing to install: this file belongs to martin-francois/symphony-trello. 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/martin-francois/symphony-trello/main/.codex/skills/debug/SKILL.mdgit clone --depth 1 https://github.com/martin-francois/symphony-trelloWrote 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/martin-francois/symphony-trello/debug)<a href="https://agentmods.dev/skills/martin-francois/symphony-trello/debug"><img src="https://agentmods.dev/badge/skills/martin-francois/symphony-trello/debug/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/martin-francois/symphony-trello/debug"><img src="https://agentmods.dev/badge/skills/martin-francois/symphony-trello/debug.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 | $0.00044 | $0.00874 |
| Opus 5 | $0.00022 | $0.00437 |
| Sonnet 5 | $0.00009 | $0.00175 |
| Haiku 4.5 | $0.00004 | $0.00087 |
Grade A, and why
debug scanned grade A with 1 finding 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 8d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -fsS http://127.0.0.1:18080/api/v1/state | jq How it starts
The opening of the file, as written. The whole thing — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Debug
Goals
- Determine whether the problem is Trello routing, scheduler state, Codex execution, filesystem access, credentials, or handoff tooling.
- Use safe identifiers and avoid exposing secrets or private local paths.
- Leave enough evidence for the next agent to continue.
Inputs
- Trello card title or short link.
- The workflow file for the board.
- The status page or
/api/v1/state. - Service logs from the local run or deployment.
- Recent Trello comments on the card.
Triage Flow
- Confirm the service is reading the intended workflow file and Trello board.
- Run
symphony-trello diagnosticswhen the installed command is available. This gives a public-safe overview of connected boards, workflows, health probes, and recent logs. - If the failure depends on information the default report intentionally omits,
run
symphony-trello diagnostics --deepto add deeper public-safe checks such as Codex and GitHub auth-status probes. - If the diagnostics output contains
board_hash,key_hash, or<path:...>tokens that you need to map back to local objects, runsymphony-trello diagnostics --show-private-contextlocally. Add--boardor--workflowwhen you can narrow the scope. Treat this output as private investigation data: use it to inspect the right board, workflow, env file, workspace, state directory, or log file, but do not paste it into GitHub, Trello, committed files, or user-facing summaries. - Open
/api/v1/stateand check:- queued candidates
- running cards
- retrying cards
- last Codex event and message
- token totals and rate-limit data
- Check the card's current Trello list. Cards in non-active lists are not dispatched.
- Read recent Trello comments on the card. Blocker comments often describe the requested path, the per-card workspace, auth, or permission problem without copying private host paths into Trello-visible text.
- Search logs by card identifier, worker identity, and session id. Prefer
rg. - Classify the failure:
- Trello credentials or board access.
- Workflow parse or invalid config.
- No eligible active cards.
- Codex app-server startup/auth failure.
- Codex turn timeout or stall.
- Filesystem sandbox or allowed-root blocker.
- Trello handoff tool failure.
- Fix the smallest cause, then rerun a local or deployed live verification that exercises the same path.
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.
- 8d ago First seen · 96 lines · 44 tokens per session scan A a030c1370e8d
debug is a skill published in the GitHub repository martin-francois/symphony-trello (2 stars, last pushed today), licensed Apache-2.0. It adds 44 tokens to every session and 874 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
langsmith-tracing
LangSmith tracing and debugging setup for LLM applications. Configure observability, capture traces, and enable debugging for LangChain/LangGraph agents.
behavior-contract
Bug condition/postcondition formalization as testable Behavior Contracts. Defines invariants that must be preserved across fixes.
quality-hooks
Language-specific auto-lint/format/typecheck pipeline. Supports Python (ruff+pyright), TypeScript (prettier+eslint+tsc), Go (gofmt+golangci-lint). Auto-fix and convergence loops.
debugging-patterns
Root cause analysis frameworks including log-first investigation, git bisect correlation, and pattern-based diagnosis with confidence scoring.
systematic-debugging
Structured debugging methodology using hypothesis-driven investigation, log analysis, and bisection to isolate and resolve defects.
hotfix-triage
Urgent issue classification, root cause analysis, and fast-path routing for production hotfixes.