Symphony turns project tasks into isolated implementation runs handled autonomously by coding agents, with work tracked through a Linear board. Teams use it to manage engineering work at a higher level instead of supervising each agent. The catalogue includes seven skills associated with Symphony.
Borrowing it
Nothing to install: this file belongs to openai/symphony. 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/openai/symphony/main/.codex/skills/debug/SKILL.mdgit clone --depth 1 https://github.com/openai/symphonyWrote 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/openai/symphony/debug)<a href="https://agentmods.dev/skills/openai/symphony/debug"><img src="https://agentmods.dev/badge/skills/openai/symphony/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/openai/symphony/debug"><img src="https://agentmods.dev/badge/skills/openai/symphony/debug.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Snyk pass
- NVIDIA SkillSpector pass
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 | $0.00033 | $0.01073 |
| Opus 5.5 | $0.00013 | $0.00429 |
| Sonnet 5.5 | $0.00007 | $0.00215 |
| Haiku 4.5 | $0.00003 | $0.00107 |
Grade A, and why
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 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 — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Debug
Goals
- Find why a run is stuck, retrying, or failing.
- Correlate Linear issue identity to a Codex session quickly.
- Read the right logs in the right order to isolate root cause.
Log Sources
- Primary runtime log:
log/symphony.log- Default comes from
SymphonyElixir.LogFile(log/symphony.log). - Includes orchestrator, agent runner, and Codex app-server lifecycle logs.
- Default comes from
- Rotated runtime logs:
log/symphony.log*- Check these when the relevant run is older.
Correlation Keys
issue_identifier: human ticket key (example:MT-625)issue_id: Linear UUID (stable internal ID)session_id: Codex thread-turn pair (<thread_id>-<turn_id>)
elixir/docs/logging.md requires these fields for issue/session lifecycle logs. Use
them as your join keys during debugging.
Quick Triage (Stuck Run)
- Confirm scheduler/worker symptoms for the ticket.
- Find recent lines for the ticket (
issue_identifierfirst). - Extract
session_idfrom matching lines. - Trace that
session_idacross start, stream, completion/failure, and stall handling logs. - Decide class of failure: timeout/stall, app-server startup failure, turn failure, or orchestrator retry loop.
Commands
# 1) Narrow by ticket key (fastest entry point)
rg -n "issue_identifier=MT-625" log/symphony.log*
# 2) If needed, narrow by Linear UUID
rg -n "issue_id=<linear-uuid>" log/symphony.log*
# 3) Pull session IDs seen for that ticket
rg -o "session_id=[^ ;]+" log/symphony.log* | sort -u
# 4) Trace one session end-to-end
rg -n "session_id=<thread>-<turn>" log/symphony.log*
# 5) Focus on stuck/retry signals
rg -n "Issue stalled|scheduling retry|turn_timeout|turn_failed|Codex session failed|Codex session ended with error" log/symphony.log*
Investigation Flow
- Locate the ticket slice:
- Search by
issue_identifier=<KEY>. - If noise is high, add
issue_id=<UUID>.
- Search by
- Establish timeline:
- Identify first
Codex session started ... session_id=.... - Follow with
Codex session completed,ended with error, or worker exit lines.
- Identify first
- Classify the problem:
- Stall loop:
Issue stalled ... restarting with backoff. - App-server startup:
Codex session failed .... - Turn execution failure:
turn_failed,turn_cancelled,turn_timeout, orended with error. - Worker crash:
Agent task exited ... reason=....
- Stall loop:
- Validate scope:
- Check whether failures are isolated to one issue/session or repeating across multiple tickets.
- Capture evidence:
- Save key log lines with timestamps,
issue_identifier,issue_id, andsession_id. - Record probable root cause and the exact failing stage.
- Save key log lines with timestamps,
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 First seen · 119 lines · 33 tokens per session scan A f043ad96235e
debug is a skill published in the GitHub repository openai/symphony (27,807 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 33 tokens to every session and 1,073 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
systematic-debugging
Use when debugging a failing test, build error, or runtime issue that isn't immediately obvious. Guides a 4-phase root cause analysis instead of random fix attempts.
log-error-digest
Analyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or…
deck-retro
Run a fully local agent-deck retrospective over the user's own transcripts, Recall index and logs. Use when a user wants to find recurring failures or take their own finding from investigation through synthetic reproduction, a user-filed issue, a test-first fix and contributor PR handoff. Also use for weekly usage…
cwv-optimizer
Diagnose and fix Core Web Vitals issues on AEM Edge Delivery Services pages. Goes deeper than generic CWV advice by understanding EDS-specific performance patterns including the 100KB LCP budget, E-L-D loading phases, block rendering behavior, and third-party script impact. Produces specific fixes for LCP, CLS, and…
incident-response-incident-response
Coordinate production incident triage, mitigation, investigation, recovery, and follow-up. Use when responding to outages or other incidents that require structured operational coordination.