fire-analytics

A command for reviewing how the project's skills have been used, including their results, time savings, and success rates.

In plain words
What is it for?
Use it to inspect usage by category or time period, review time saved, find gaps, and export reports as Markdown, JSON, or CSV.
Why use it?
It shows which skills help, where they fall short, and what the project may be missing. This makes future skill choices easier to judge.

Command

Install

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.

agentmods
npx agentmods add commands/thierryn/fire-flow/fire-analytics
Clone the repo
git clone --depth 1 https://github.com/ThierryN/fire-flow
Per session 7 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 5,634 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00007 $0.05634
Opus 5 $0.00003 $0.02817
Sonnet 5 $0.00001 $0.01127
Haiku 4.5 $0.00001 $0.00563

Measured 2d ago against content hash b5340c2f6666, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

fire-analytics 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.

commands/fire-analytics.md · 500 lines

How it starts

The opening of the file, as written. The whole thing — 500 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/fire-analytics

Skills usage analytics with effectiveness metrics and learning insights


Purpose

Analyze skills library usage patterns across the project. Shows which skills have been applied, their effectiveness, time savings, success rates, and identifies gaps in the skills repertoire. Helps optimize skill selection for future phases.


Arguments

Argument Required Description
--category [name] No Filter to specific category (e.g., database-solutions)
--time-saved No Focus on time savings report
--gaps No Identify missing skills and recommendations
--period [days] No Limit analysis to last N days (default: all time)
--export [format] No Export report as md, json, or csv

Process

Step 1: Load Analytics Data

Read skills usage data from project state files.

# Required files
SKILLS_INDEX=".planning/SKILLS-INDEX.md"
STATE_FILE=".planning/CONSCIENCE.md"
SUMMARIES=".planning/phases/*/RECORD.md"

if [ ! -f "$SKILLS_INDEX" ]; then
  echo "No skills data found. Run /fire-search or /fire-3-execute first."
  exit 1
fi

Parse:

  • .planning/SKILLS-INDEX.md - Skills applied per phase/plan
  • .planning/CONSCIENCE.md - Analytics section with usage stats
  • .planning/phases/*/RECORD.md - Skills applied per execution
  • Git history - Time between commits for duration estimates

Step 2: Compute Analytics

Calculate usage statistics and effectiveness metrics:

Usage Statistics:
- Skills by usage count (descending)
- Category distribution
- Skills per phase average
- Unique skills count

Effectiveness Metrics:
- Time saved estimates (based on skill complexity ratings)
- Success rate (skills that led to passing verification)
- Impact score (performance improvements, bug prevention)

Learning Insights:
- Patterns in skill usage
- Skills that tend to be used together
- Gaps based on phase requirements vs available skills

Step 3: Display Analytics

Read the full file on GitHub · 500 lines

Changes

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.

  1. 2d ago First seen · 500 lines · 7 tokens per session scan A b5340c2f6666

Subscribe to this mod's changes

fire-analytics is a command published in the GitHub repository ThierryN/fire-flow (77 stars, last pushed 20d ago), licensed MIT. It adds 7 tokens to every session and 5,634 once invoked, about $0.0000 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.