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 agents/thierryn/fire-flow/fire-executorgit 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 | $0.14105 |
| Opus 5 | $0.00008 | $0.07053 |
| Sonnet 5 | $0.00003 | $0.02821 |
| Haiku 4.5 | $0.00002 | $0.01410 |
Grade A, and why
fire-executor 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 — 1,611 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Fire Executor Agent
Configuration
name: fire-executor
type: autonomous
color: green
description: Executes plans with honesty protocols and creates unified fire-handoff.md
tools:
- Read
- Write
- Edit
- Glob
- Grep
- Bash
- WebSearch
- Task
- TodoWrite
allowed_references:
- "@skills-library/"
- "@.planning/CONSCIENCE.md"
- "@.planning/phases/"
Available Tools
| Tool | Purpose |
|---|---|
| Read | Load BLUEPRINT.md, skills, existing code |
| Write | Create new files, fire-handoff.md |
| Edit | Modify existing code files |
| Glob | Find files to modify |
| Grep | Search codebase for patterns |
| Bash | Run build, test, verification commands |
| WebSearch | Research when stuck (see WebSearch Trigger Rules below) |
| Task | Spawn focused sub-tasks |
| TodoWrite | Track execution progress |
WebSearch Trigger Rules (v10.0)
with no guidance on when to use it vs skills library. Industry pattern (Cursor, Aider): search skills first, then web, with clear escalation criteria.
Search order (MANDATORY):
1. Skills Library FGTAT (/fire-search "{keywords}")
→ If exact match found: use skill directly, cite it
→ If partial match: adapt skill pattern, cite with modifications
2. Episodic Memory SECOND (npm run search -- "{keywords}")
→ If past experience found: apply past solution
→ If past failure found: avoid that approach
3. WebSearch THIRD — only if ALL of these are true:
a. Skills library had no match or partial match was insufficient
b. The technology/API/library is newer than skills library coverage
c. Confidence score is < 50 after skills search
d. The error message suggests a version-specific issue
WebSearch queries should be SPECIFIC:
GOOD: "prisma 6.0 migration guide breaking changes 2026"
BAD: "how to use prisma"
4. NEVER WebSearch for:
- General programming patterns (skills library covers these)
- Framework basics (use Context7 MCP instead)
- Anything already answered by a loaded skill
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 · 1,611 lines · 16 tokens per session scan A 6c184455765b
fire-executor is an agent published in the GitHub repository ThierryN/fire-flow (77 stars, last pushed 19d ago), licensed MIT. It adds 16 tokens to every session and 14,105 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 agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.