agentleFS
Sign inStart free
Manavarya09Manavarya09/cost-guardian/skills/cost-insights/SKILL.md

cost-insights

Skill35 starsChanged 7 months agoMITView on GitHub

Advanced cost intelligence: efficiency scoring, waste detection, ROI metrics, model savings calculator, anomaly detection, and GitHub badge generation. Use when user says 'insights', 'efficiency', 'waste', 'roi', 'savings', 'anomaly', 'badge', or '/cost-insights'.

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 2 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Check if this session is abnormally expensive:

    line 43
  2. Distinctive:

    Always suggest actionable improvements for low scores

    line 57

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Cost Insights

Advanced cost intelligence that goes beyond simple tracking. Shows WHERE money is wasted, WHAT you got for your spend, and HOW to spend less.

Commands

/cost-insights or /cost-insights report (default)

Full insights report with all metrics:

node "${CLAUDE_SKILL_DIR}/../../scripts/insights.js" insights "${CLAUDE_SESSION_ID}"

Display the ASCII output as-is.

/cost-insights waste

Detailed waste analysis — redundant reads, failed commands, retry storms:

node "${CLAUDE_SKILL_DIR}/../../scripts/insights.js" waste "${CLAUDE_SESSION_ID}"

Explain each waste type and suggest how to avoid it.

/cost-insights roi

Cost-per-line and cost-per-commit ROI metrics:

node "${CLAUDE_SKILL_DIR}/../../scripts/insights.js" roi "${CLAUDE_SESSION_ID}"

Compare to typical benchmarks ($0.02-0.05/line is good, >$0.10/line is expensive).

/cost-insights savings

Model routing savings calculator — shows what you could save on cheaper models:

node "${CLAUDE_SKILL_DIR}/../../scripts/insights.js" savings "${CLAUDE_SESSION_ID}"

Explain which tasks could safely use Haiku vs Sonnet vs Opus.

/cost-insights anomaly

Check if this session is abnormally expensive:

node "${CLAUDE_SKILL_DIR}/../../scripts/insights.js" anomaly "${CLAUDE_SESSION_ID}"

/cost-insights badge [daily|weekly|monthly]

Generate a GitHub README badge showing AI development cost:

node "${CLAUDE_SKILL_DIR}/../../scripts/insights.js" badge monthly

Give the user the markdown to paste in their README.

Response Guidelines

  • Efficiency scores: 80-100 = great, 60-79 = good, 40-59 = needs work, <40 = poor
  • Always suggest actionable improvements for low scores
  • For waste: explain WHY each waste happens and HOW to avoid it
  • For savings: be honest that model routing requires task-type awareness
  • For badges: output the markdown they can paste directly

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free