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 commands/thierryn/fire-flow/fire-debuggit clone --depth 1 https://github.com/ThierryN/fire-flowWhat 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 | $0.00016 | $0.04672 |
| Opus 5 | $0.00008 | $0.02336 |
| Sonnet 5 | $0.00003 | $0.00934 |
| Haiku 4.5 | $0.00002 | $0.00467 |
Grade A, and why
fire-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 2d 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 — 659 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/fire-debug
Systematic debugging with scientific method, persistent state recovery, and WARRIOR skills integration
Purpose
Debug issues using scientific method with subagent isolation. Combines Dominion Flow's proven debug orchestration with skills library (debugging patterns, domain knowledge) and honesty protocols.
Orchestrator role: Gather symptoms, spawn fire-debugger agent, handle checkpoints, spawn continuations.
Why subagent: Investigation burns context fast (reading files, forming hypotheses, testing). Fresh 200k context per investigation. Main context stays lean for user interaction.
Arguments
arguments:
issue_description:
required: false
type: string
description: "Brief description of the issue to debug"
example: "/fire-debug login fails with 500 error"
optional_flags:
--diagnose-only: "Find root cause but don't fix (for plan-based fixes)"
--verbose: "Show detailed investigation progress"
Process
Step 1: Check Active Debug Sessions
ls .planning/debug/*.md 2>/dev/null | grep -v resolved | head -5
If active sessions exist AND no arguments:
- Display sessions with status, hypothesis, next action
- User picks number to resume OR describes new issue
If arguments provided OR user describes new issue:
- Continue to symptom gathering
Step 2: WARRIOR Enhancement - Skills Check + Context7 Live Docs
Before investigating, check skills library for relevant debugging patterns:
/fire-search "[error type] debugging"
/fire-search "[technology] troubleshooting"
Load applicable skills:
@skills-library/debugging/patterns@skills-library/[domain]/domain knowledge@skills-library/integrations/if external service involved
Context7 Live Documentation Lookup (v5.0):
If the issue involves a specific library/framework, pull current docs:
# Resolve the library
mcp__plugin_context7_context7__resolve-library-id(libraryName="{library}")
# Query for relevant API docs, known issues, migration notes
mcp__plugin_context7_context7__query-docs(libraryId="{resolved-id}", query="{specific error}")
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.
- 2d ago First seen · 659 lines · 16 tokens per session scan A 8fe4c63134e9
fire-debug is a command published in the GitHub repository ThierryN/fire-flow (77 stars, last pushed 20d ago), licensed MIT. It adds 16 tokens to every session and 4,672 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 2026-08-30.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.