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/kwanpham2195/symphony-go/debugnpx skills add kwanpham2195/symphony-go --skill debuggit clone --depth 1 https://github.com/kwanpham2195/symphony-goWrote 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/kwanpham2195/symphony-go/debug)<a href="https://agentmods.dev/skills/kwanpham2195/symphony-go/debug"><img src="https://agentmods.dev/badge/skills/kwanpham2195/symphony-go/debug.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 | $0.00030 | $0.00452 |
| Opus 5 | $0.00015 | $0.00226 |
| Sonnet 5 | $0.00006 | $0.00090 |
| Haiku 4.5 | $0.00003 | $0.00045 |
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 4d 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.
What it actually says
Debug
Goals
- Find why a run is stuck, retrying, or failing.
- Correlate Linear issue identity to a Codex session quickly.
Correlation Keys
issue_identifier: human ticket key (e.g.,ENG-44)issue_id: Linear UUIDsession_id: Codex thread-turn pair (<thread_id>-<turn_id>)
Quick Triage
- Find recent logs for the ticket by
issue_identifier. - Extract
session_idfrom matching lines. - Trace that
session_idacross start, stream, completion/failure, and stall handling. - Classify: timeout/stall, app-server startup failure, turn failure, or orchestrator retry loop.
Commands
# Search by ticket key
rg -n "issue_identifier=ENG-44" /path/to/logs
# Pull session IDs for that ticket
rg -o "session_id=[^ ;]+" /path/to/logs | sort -u
# Trace one session end-to-end
rg -n "session_id=<thread>-<turn>" /path/to/logs
# Focus on stuck/retry signals
rg -n "stalled|scheduling retry|turn_timeout|turn_failed|session failed" /path/to/logs
Classification
| Pattern | Cause |
|---|---|
stalled.*restarting with backoff |
No codex activity beyond stall_timeout_ms |
session failed |
App-server startup error |
turn_failed / turn_cancelled |
Turn execution failure |
agent failed.*scheduling retry |
Worker error, will retry with backoff |
| Repeated dispatch + immediate failure | Config error or workspace issue |
Dashboard
If the HTTP server is running, check /api/v1/state for current running sessions and retry queue state. Check /api/v1/issues/<identifier> for issue-specific debug info.
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.
- 4d ago First seen · 58 lines · 30 tokens per session scan A 528859e45edb
debug is a skill published in the GitHub repository kwanpham2195/symphony-go (10 stars, last pushed 3mo ago), licensed MIT. It adds 30 tokens to every session and 452 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
codex-symphony
Install and operate a portable OpenAI Symphony + Linear orchestration setup in any Git repository. Use when the user wants a one-command local Symphony runner, a reusable WORKFLOW template, background launch scripts, or a Codex wrapper that restarts Symphony automatically when reopening the CLI.
linear-cli
Manage Linear issues from the command line using the linear cli. This skill allows automating linear management.
Release
This skill should be used when the user asks to "make a release", "create a release", "cut a release", "release a new version", "publish a release", or mentions preparing for release. Provides comprehensive workflow for reviewing changes, updating changelog, determining semver bump, and publishing.
release-core-test
Invoke when dev-testing a Cyrus change that spans CYPACK (edgeworker + CLI) and CYHOST (Vercel-hosted GUI) and the hosted GUI needs to point at an unreleased cyrus-core from this repo. Publishes cyrus-core (and claude-runner if needed) as a -test.N prerelease under the npm test dist-tag so CYHOST can install it via…
cyrus-setup-claude-auth
Configure Claude Code authentication for Cyrus — API key, OAuth token, or third-party provider.
f1-test-drive
Orchestrate F1 test drives to validate the Cyrus agent system end-to-end across issue-tracker, EdgeWorker, and activity rendering.