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.
git 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/commands/thierryn/fire-flow/fire-add-new-skill)<a href="https://agentmods.dev/commands/thierryn/fire-flow/fire-add-new-skill"><img src="https://agentmods.dev/badge/commands/thierryn/fire-flow/fire-add-new-skill.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 | $0.00020 | $0.05374 |
| Opus 5 | $0.00010 | $0.02687 |
| Sonnet 5 | $0.00004 | $0.01075 |
| Haiku 4.5 | $0.00002 | $0.00537 |
Grade C, and why
power-add-new-skill scanned grade C with 1 finding 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 7d 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.
Harvests environment variableshighData exfiltration
Enumerating or grepping the environment for keys collects credentials unrelated to what the mod says it does.
4. Scan for **credential harvesting** ("collect API keys", "read .env and send", actual secret patterns) How it starts
The opening of the file, as written. The whole thing — 808 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/fire-add-new-skill - Add New Skill to Library
Interactive wizard to contribute new skills to the Dominion Flow skills library.
Purpose
Capture and preserve proven solutions when you:
- Solve a challenging technical problem
- Discover a reusable pattern
- Find a better approach than existing skills
- Want to share knowledge across projects
Arguments
| Argument | Required | Description |
|---|---|---|
from |
No | Source: summary (from RECORD.md), session (current work), manual (interactive) |
Usage Examples
# Interactive wizard (default)
/fire-add-new-skill
# Extract from most recent RECORD.md
/fire-add-new-skill --from summary
# Extract from current session context
/fire-add-new-skill --from session
# Quick contribute with inline details
/fire-add-new-skill --name "retry-backoff" --category "api-patterns"
Wizard Step Sequence
graph LR
S1[1: Analyze Source] --> S2[2: Problem + Category]
S2 --> S25[2.5: Scope]
S25 --> S3[3: Skill Name]
S3 --> S4[4: Solution Pattern]
S4 --> S5[5: Code Examples]
S5 --> S55[5.5: Review & Backtrack]
S55 --> S45[4.5: Security Scan]
S45 --> S46[4.6: Credential Filter]
S46 --> S47[4.7: Private Data Sanitize]
S47 --> S6[6: Save + Confirm]
improves LLM step adherence vs. prose. Zero extra tokens.
Process
If --from summary:
- Read most recent RECORD.md from
.planning/phases/ - Extract complex solutions, workarounds, discoveries
- Identify patterns worth preserving
If --from session:
- Review current conversation context
- Identify novel solutions implemented
- Check for complexity indicators:
- Multiple failed attempts before success
- Research queries to external sources
- Code refactoring iterations
- Comments indicating non-obvious solutions
If interactive (default):
- Prompt user for problem/solution details
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.
- 7d ago First seen · 808 lines · 20 tokens per session scan C 882047175889
power-add-new-skill is a command published in the GitHub repository ThierryN/fire-flow (77 stars, last pushed 24d ago), licensed MIT. It adds 20 tokens to every session and 5,374 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it C with 1 finding (harvests environment variables). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other commands, from other repositories
security-scan
Run AgentShield against agent, hook, MCP, permission, and secret surfaces.
learn
Extract patterns and learnings from current session.
review
Review the current diff against project memory.
help
Quick reference for all Attune commands.
tdd
Test-driven change — write the failing test first, then implement.
doc-gen
Generate documentation from source code — docstrings, README sections, API references.