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-skills-history)<a href="https://agentmods.dev/commands/thierryn/fire-flow/fire-skills-history"><img src="https://agentmods.dev/badge/commands/thierryn/fire-flow/fire-skills-history/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/thierryn/fire-flow/fire-skills-history"><img src="https://agentmods.dev/badge/commands/thierryn/fire-flow/fire-skills-history.svg" alt="Reviewed on agentmods" width="80" 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 | $0.02457 |
| Opus 5 | $0.00008 | $0.01229 |
| Sonnet 5 | $0.00003 | $0.00491 |
| Haiku 4.5 | $0.00002 | $0.00246 |
Grade A, and why
power-skills-history 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 11d 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 — 389 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/fire-skills-history - View Skill Version History
View the complete version history, changelogs, and contributors for any skill.
Purpose
- Track how a skill has evolved over time
- See who contributed improvements
- Understand why changes were made
- Find previous versions if needed
- Review skill maturity and stability
Prerequisites
The skills library must be git-versioned:
~/.claude/plugins/dominion-flow/skills-library/.git/~/.claude/fire-skills-global/.git/(for global library)
Arguments
| Argument | Required | Description |
|---|---|---|
skill |
Yes | Skill path: {category}/{skill-name} |
Usage Examples
# View history for a specific skill
/fire-skills-history database-solutions/n-plus-1
# View history with full commit details
/fire-skills-history security/jwt-auth --verbose
# View history from global library
/fire-skills-history api-patterns/pagination --global
# Show only last N versions
/fire-skills-history performance/caching --limit 5
# Export history to file
/fire-skills-history testing/snapshot --export
Process
Check if the skill file exists:
# Check project library
ls ~/.claude/plugins/dominion-flow/skills-library/{category}/{skill-name}.md
# Check global library (if --global)
ls ~/.claude/fire-skills-global/{category}/{skill-name}.md
If not found:
Error: Skill not found: {category}/{skill-name}
Did you mean one of these?
- {similar-skill-1}
- {similar-skill-2}
Search for skills: /fire-search "{skill-name}"
Query git log for the skill file:
cd ~/.claude/plugins/dominion-flow/skills-library
git log --follow --format="%H|%ai|%an|%s" -- {category}/{skill-name}.md
Parse each commit:
- Hash: Full commit SHA
- Date: Commit timestamp
- Author: Contributor name
- Message: Commit description
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.
- 11d ago First seen · 389 lines · 15 tokens per session scan A 6a012617e9bb
power-skills-history is a command published in the GitHub repository ThierryN/fire-flow (77 stars, last pushed 28d ago), licensed MIT. It adds 15 tokens to every session and 2,457 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
export-closedloop-learnings
Exports pending ClosedLoop learnings to global location with deduplication.
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.
rc-plano
Fluxo Explore→Plan — investiga antes de codar e entrega um plano para aprovação.
lfe-improve-architecture
Find deepening opportunities in the codebase — turn shallow modules into deep ones. Use in Phase 5 (Hygiene sub-pipeline) or when scheduled by session count.