Agent skill

Cost Diff

by ruvnet in ruvnet/ruflo

Snapshot delta between two cost-summary JSON outputs. An agent skill from ruvnet/ruflo.

MITAuto-check: notes

Install Cost Diff

skills CLI
$ npx skills add ruvnet/ruflo --skill cost-diff -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install ruvnet/ruflo cost-diff --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/ruvnet/ruflo.git skills-src && mkdir -p .claude/skills && cp -r skills-src/plugins/ruflo-cost-tracker/skills/cost-diff .claude/skills/cost-diff && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
cost-diff
GitHub stars
74k
Token cost
~1.3k tokens
SKILL.md length
474 words
Files
1
Skills in repo
264
Repo updated
First seen
Licence
MIT

At a glance

Snapshot delta between two cost-summary JSON outputs. An agent skill from ruvnet/ruflo.

  • Works in 7 steps: Load --baseline and --current JSON… → Sanity check: both must have… → Per-key delta: byTier… → …
  • SKILL.md covers Algorithm, PR-gate workflow, --alert-on-class-pct (iter 86) and Smoke transcript (synthetic…, plus 3 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Cost Diff is an agent skill from ruvnet/ruflo. Snapshot delta between two cost-summary JSON outputs. PR-level cost regression detection — answers "what changed between these two specific snapshots?". Pairs with cost-summary's stable JSON contract.

Its SKILL.md is about 1.3k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

The repository describes itself as: 🌊 The original agent harness. Deploy intelligent multi-player swarms, coordinate autonomous workflows, and build conversational AI systems. Features adaptive memory…. The licence is MIT.

Example prompts

  • “what changed between these two specific snapshots?”
  • “/cost-diff”

Requirements

  • Pre-approved tools (allowed-tools): Bash

Workflow steps

7 steps, taken from the first numbered list in SKILL.md.

  1. Load --baseline and --current JSON snapshots.
  2. Sanity check: both must have total_cost_usd + sessionCount (cost-summary shape).
  3. Per-key delta: byTier (haiku/sonnet/opus) and byModel (each model).
  4. Each entry tagged added / removed / changed based on
  5. Sort table by |delta| descending so the biggest movers are at the top.
  6. alert-on-pct N: exit 1 when total_pct > N.
  7. alert-on-usd N: exit 1 when total_delta_usd > N.

What it can do on your machine

Read from SKILL.md and the folder at commit de590e1. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves these tools, so the agent can use them without asking each time:

    • Bash

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are bash).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Cost Diff loads about 1.3k tokens when it runs. Until then it costs about 53 tokens; SKILL.md has 474 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~53
When it runs · the whole SKILL.md, loaded when a task matches
~1.3k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check: notes

The automated check noted patterns worth knowing about, such as sudo or a known installer.

  • NotePre-approves every shell command (allowed-tools: Bash)SKILL.md
    allowed-tools: Bash

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from ruvnet/ruflo at commit de590e1, republished under its MIT licence (© ruvnet). 474 words, ~1,254 tokens.

Download SKILL.mdSave it as .claude/skills/cost-diff/SKILL.md (or your agent's skills folder).
name
cost-diff
description
Snapshot delta between two cost-summary JSON outputs. PR-level cost regression detection — answers "what changed between these two specific snapshots?". Pairs with cost-summary's stable JSON contract.
allowed-tools
Bash
argument-hint
--baseline <baseline.json> --current <current.json> [--alert-on-pct N] [--alert-on-usd N] [--alert-on-class-pct <class>:N[,<class>:N]] [--format table|json]

PR-level cost regression detection. Where cost-counterfactual compares to HYPOTHETICAL baselines (always-haiku/sonnet/opus) and cost-burn compares latest bucket to PRIOR MEAN, cost-diff compares two SPECIFIC known-good snapshots.

QuestionSkill
"What would we have spent at always-X?"cost-counterfactual
"Is daily burn accelerating vs prior mean?"cost-burn
"Did THIS PR add spend vs main?"cost-diff ← this

Algorithm

Implementation: scripts/diff.mjs. Consumes the stable JSON contract from cost summary --format json.

  1. Load --baseline and --current JSON snapshots.
  2. Sanity check: both must have total_cost_usd + sessionCount (cost-summary shape).
  3. Per-key delta: byTier (haiku/sonnet/opus) and byModel (each model).
  4. Each entry tagged added / removed / changed based on baseline / current zero-ness.
  5. Sort table by |delta| descending so the biggest movers are at the top.
  6. --alert-on-pct N: exit 1 when total_pct > N.
  7. --alert-on-usd N: exit 1 when total_delta_usd > N. Both can be set; first to trigger wins.

PR-gate workflow

bash
# Capture baseline (e.g. on main, via the cost-tracker-smoke CI workflow)
cost summary --format json > baseline.json

# On the PR branch, capture current state
cost summary --format json > current.json

# Compare; fail the PR if total spend grew >10% OR >$5
cost diff --baseline baseline.json --current current.json \
          --alert-on-pct 10 --alert-on-usd 5.00

The combination of both flags catches:

  • Percent-only fires: a small absolute change but a meaningful shift (e.g. doubling from $0.10 to $0.20 hits +100% but only +$0.10).
  • USD-only fires: a large absolute change with a small percent (e.g. growing from $100 to $110 is only +10% but +$10).

Either signal can fail the PR independently — they're OR'd.

--alert-on-class-pct (iter 86)

The two USD-level thresholds above miss a regression class: when ONE token type grows disproportionately even though total spend grows modestly. Example: a PR introduces a verbose context-cache pattern, total spend grows only 10% (under --alert-on-pct 50), but cache_write tokens grow 900%. The iter-82 driver hides inside the USD signal.

--alert-on-class-pct cache_write:50 exits 1 when cache_write tokens grow more than 50% baseline → current. Multiple classes can be checked in one flag (comma-separated):

bash
cost diff --baseline baseline.json --current current.json \
          --alert-on-class-pct cache_write:50,output:25

First class to breach wins. Valid classes: input | output | cache_write | cache_read.

Recommended PR-gate triad:

bash
cost diff --baseline ... --current ... \
          --alert-on-pct 25 \
          --alert-on-usd 5.00 \
          --alert-on-class-pct cache_write:100

Three orthogonal signals — pct (total grew), usd (large absolute jump), class-pct (composition shifted). Each catches what the others miss; AND-of-OR semantics means any one firing fails the PR.

Show full SKILL.md (157 more words)Show less

Smoke transcript (synthetic baseline + current)

| Total spend       | $1.000000 | $1.500000 | +$0.500000 | 50.00% |
| Sessions          | 10        | 13        | +3         | 30.00% |

## By tier
| opus   | $0      | $0.60   | +$0.600000 | new      | added   |
| sonnet | $0.70   | $0.50   | -$0.200000 | -28.57%  | changed |
| haiku  | $0.30   | $0.40   | +$0.100000 | 33.33%   | changed |

Notice the table is sorted by absolute delta, not alphabetically — the biggest mover (opus newly added) bubbles to the top. Operators reading top-down see "what mattered" first.

Exit codes

ExitMeaning
0No alert, OR no thresholds set
1--alert-on-pct or --alert-on-usd threshold exceeded
2Config error (missing files, invalid JSON, malformed snapshot)

Status column

StatusMeaning
addedThis tier/model was $0 in baseline, >$0 in current
removedThis tier/model was >$0 in baseline, $0 in current
changedBoth baseline and current >$0; delta is the difference

Entries with baseline === 0 && current === 0 are dropped (nothing to report).

Composition with cost-summary

cost-diff is the SECOND HALF of a contract that cost-summary started: the stable JSON shape from cost summary --format json. Both pieces have been frozen — adding fields to summary is fine; renaming or removing isn't.

If you're consuming snapshots elsewhere (dashboards, alerting), the same shape works — cost-diff is just one consumer.

© ruvnet, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in plugins/ruflo-cost-tracker/skills/cost-diff of ruvnet/ruflo.

Open the folder on GitHubat commit de590e1

Compare with similar skills

Cost Diff next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Cost Diff compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Cost Diff this skillruvnet/ruflo74k—~1.3kAutomated safety check: NotesMIT
Cost Trackingaffaan-m/ECC274k1 repos~1.3kAutomated safety check: PassMIT
Cost Trackingaffaan-m/ECC274k—~829Automated safety check: PassMIT
Analyze Cloud Costslangfuse/langfuse35k—~672Automated safety check: PassCustom licence
Output Dev Workflow Costgrowthxai/output440—~1.4kAutomated safety check: NotesApache-2.0
Cloud Cost Optimizationwshobson/agents40k13 repos~1.7kAutomated safety check: PassMIT

Similar skills

  • Cost Tracking

    affaan-m/ECC

    Track and report Claude Code token usage, spending, and budgets from the local ECC cost-tracker metrics log.

    274k GitHub starsUsed in 1 repo~1.3k tokens
    AI & LLM EngineeringAuto-check passed
  • Cost Tracking

    affaan-m/ECC

    ローカルのコスト追跡データベースからClaude Codeのトークン使用量、支出、予算を追跡・レポートします。コスト、支出、使用量、トークン、予算、またはプロジェクト、ツール、セッション、日付によるコスト内訳について質問する場合に使用します。

    274k GitHub stars~829 tokensUpdated 2 days ago
    AI & LLM EngineeringAuto-check passed
  • Analyze Cloud Costs

    langfuse/langfuse

    Analyze Langfuse Cloud infrastructure cost structure using Metabase cost marts.

    35k GitHub stars~672 tokensUpdated today
    DevOps & CloudAuto-check passed
  • Output Dev Workflow Cost

    growthxai/output

    Calculate and display the cost of an Output SDK workflow execution run.

    440 GitHub stars~1.4k tokensUpdated today
    AI & LLM EngineeringAuto-check: notes
  • Cuts cloud spend across AWS, Azure, GCP and OCI with cost tagging, rightsizing, commitment and spot pricing models, and architecture changes.

    40k GitHub starsUsed in 13 repos~1.7k tokens
    DevOps & CloudAuto-check passed
  • Accesslint Diff

    sickn33/agentic-awesome-skills

    Diff a live page's accessibility violations against a baseline — by default compares uncommitted changes (stash-based), or pass --branch [<name] to diff against a branch.

    47k GitHub starsUsed in 1 repo~1.2k tokens
    Frontend & DesignAuto-check passed

More from ruvnet/ruflo

All 264 skills in this repo
  • Stores, searches, and retrieves successful patterns with HNSW-indexed semantic search so agents can reuse past solutions instead of relearning them.

    74k GitHub starsUsed in 2 repos~830 tokens
    Auto-check passed
  • Runs claude-flow CLI security scans for input validation, path traversal, SQL injection, XSS, hardcoded secrets and known CVEs, and writes an audit report.

    74k GitHub starsUsed in 2 repos~823 tokens
    Auto-check passed
  • Applies the SPARC method (specification, pseudocode, architecture, refinement, completion) with 17 specialized modes and multi-agent orchestration, from research to deployment.

    74k GitHub starsUsed in 2 repos~829 tokens
    Auto-check passed
  • Coordinates a hierarchical swarm of specialized agents through the claude-flow CLI for work that spans several files or modules at once.

    74k GitHub starsUsed in 2 repos~779 tokens
    Auto-check passed
  • Sets up and drives Ruflo, an npm-installed orchestration layer for multi-agent swarms, persistent memory, routing, hooks and its MCP tool catalog.

    74k GitHub starsUsed in 1 repo~975 tokens
    Auto-check passed
  • Agent Coordination

    ruvnet/ruflo

    Reference for spawning, listing, monitoring and stopping agents with claude-flow commands, with agent type families, routing codes and coordination tips.

    74k GitHub starsUsed in 2 repos~519 tokens
    Auto-check passed

Questions about Cost Diff

What does Cost Diff do?

Snapshot delta between two cost-summary JSON outputs. An agent skill from ruvnet/ruflo. Cost Diff is an agent skill from ruvnet/ruflo. Snapshot delta between two cost-summary JSON outputs.

How do I install Cost Diff in Claude Code?

Run `npx skills add ruvnet/ruflo --skill cost-diff -a claude-code`. Or copy the skill folder (plugins/ruflo-cost-tracker/skills/cost-diff in ruvnet/ruflo) into .claude/skills/cost-diff in your project. Claude Code loads it when a task matches its description.

How do I install Cost Diff in Codex?

Run `npx skills add ruvnet/ruflo --skill cost-diff -a codex`. Or copy the skill folder (plugins/ruflo-cost-tracker/skills/cost-diff in ruvnet/ruflo) into .agents/skills/cost-diff in your project. Codex loads it when a task matches its description.

Can I use Cost Diff in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add ruvnet/ruflo --skill cost-diff -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/cost-diff, .gemini/skills/cost-diff, .github/skills/cost-diff and .opencode/skills/cost-diff in your project.

What does Cost Diff need to run?

SKILL.md names no scripts, command-line tools or credentials: Cost Diff is instructions for the agent only. Its frontmatter pre-approves these tools: Bash.

Does Cost Diff access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Cost Diff safe to install?

Our automated static check of SKILL.md found notes only (pre-approves every shell command (allowed-tools: bash)), nothing it rates as a warning. It is not a guarantee. Review the folder before installing.

What licence does Cost Diff use?

Cost Diff is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Cost Diff use?

About 1.3k tokens (SKILL.md is roughly 5k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Cost Diff?

Skills that share tags, products or a category with Cost Diff: Cost Tracking (affaan-m/ECC, 274k stars), Cost Tracking (affaan-m/ECC, 274k stars), Analyze Cloud Costs (langfuse/langfuse, 35k stars) and Output Dev Workflow Cost (growthxai/output, 440 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Cost Diff?

ruvnet (a GitHub user) maintains it in ruvnet/ruflo, which has 74,012 GitHub stars. The repository holds 264 skills in this directory. The repository was last updated on October 7, 2026.

Source: ruvnet/ruflo on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.