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 skills add ThierryN/fire-flow --skill parallel-debuggit clone --depth 1 https://github.com/ThierryN/fire-flowWrote 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/thierryn/fire-flow/parallel-debug)<a href="https://agentmods.dev/skills/thierryn/fire-flow/parallel-debug"><img src="https://agentmods.dev/badge/skills/thierryn/fire-flow/parallel-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 5.1 | $0.00015 | $0.00512 |
| Opus 5 | $0.00008 | $0.00256 |
| Sonnet 5 | $0.00003 | $0.00102 |
| Haiku 4.5 | $0.00002 | $0.00051 |
Grade A, and why
parallel-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 — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Parallel Agent Investigation Pattern (Competing Hypotheses)
Validated by Anthropic's official Agent Teams docs as the "Competing Hypotheses" pattern.
When to Use
- Complex bug affecting multiple components
- Root cause unclear after initial analysis
- Time-sensitive production issue
- Issue spans multiple files/layers
The 3-Agent Pattern
Launch all 3 in a SINGLE message (parallel execution):
// Agent 1: Where symptoms appear (child component / output layer)
Task({ subagent_type: "fire-debugger", prompt: "Investigate [symptom location]..." });
// Agent 2: What triggers it (parent/caller / data layer)
Task({ subagent_type: "fire-debugger", prompt: "Investigate [trigger source]..." });
// Agent 3: Working reference (proven patterns in codebase)
Task({ subagent_type: "Explore", prompt: "Find working examples of [similar pattern]..." });
Process
- Each agent investigates one aspect independently
- All create research documents in
.planning/research/ - Agents should actively try to disprove each other's theories (fights anchoring bias)
- Combined insights reveal root cause
- Implement fix with confidence
- Document in Skills Library (
/warrior-add-newskill)
Expected Result
Solved in ~1 hour vs 3+ hours sequential debugging.
Example Success: Video Player Bug (Feb 2, 2026)
YouTube/Vimeo videos stopping after 2-3 seconds in MERN LMS:
- Agent 1: Analyzed VideoPlayer.jsx (player lifecycle issues)
- Agent 2: Analyzed CourseContent.jsx (callback patterns causing re-renders)
- Agent 3: Found ZoomLessonPlayer (working callback refs pattern)
- Solution: Callback refs pattern identified and deployed same day
Skills Library Reference:
~/.claude/plugins/warrior-workflow/skills-library/video-media/REACT_VIDEO_PLAYER_REINITIALIZATION_FIX.md
Key Insight from Anthropic
"When the root cause is unclear, a single agent tends to find one plausible explanation and stop looking. The debate structure fights anchoring bias. The theory that survives is much more likely to be the actual root cause."
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 61 lines · 15 tokens per session scan A bedb3b573dbc
parallel-debug is a skill published in the GitHub repository ThierryN/fire-flow (77 stars, last pushed 25d ago), licensed MIT. It adds 15 tokens to every session and 512 once invoked, about $0.0001 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 2026-09-03.
Other skills, from other repositories
agent-introspection-debugging
Structured self-debugging workflow for AI agent failures using capture, diagnosis, contained recovery, and introspection reports. Use when an agent run fails and you need a reproducible diagnosis instead of a retry.
investigate
Delegate read-only investigation, debugging, audit, search, or code-understanding tasks to sub-agents; synthesize only from their structured reports.
dx-audit
Audits libraries, CLIs, and SDKs using 38 rules for public contracts, package exports, piped output, errors, and configuration. Use when asked to "audit my CLI", "review my SDK", "make this agent-friendly", or diagnose package type resolution. For agentic product trust use ax-audit; for docs use docs-writing.
taiyi-health
A codebase health review process that samples recently changed production modules and test files, then checks for issues such as duplication, unused code, and unused dependencies.
change-rollback
Undo a change already written to a ServiceNow instance — recover the prior payload from sysupdateversion, write it back without corrupting it, and know which damage update set back-out, Deleted Records, or nothing at all can reverse.
instance-performance-triage
Answer "the instance is slow" or "my nightly job never ran" from ServiceNow's own telemetry — transaction logs, syslog, systrigger, progress workers, execution trackers — instead of ad-hoc scripts that add to the load.