Codebase Cost Estimate

What it does

When your agent uses it

• Estimating how much a codebase would have cost to build with a human team
• Working out the ROI of Claude or Copilot on a repository
• Producing a ranged effort estimate with COCOMO II or Function Points

Example prompts

• “How much would it have cost a human team to build this repo?”
• “What is the ROI of using Claude on this codebase, going by the git history?”
• “Estimate this project with COCOMO and Function Points and give me P10, P50 and P90 ranges.”

Requirements

• A git repository to analyze
• Python and a shell for the bundled scripts

Workflow steps

12 steps, taken from the step headings in SKILL.md.

1. 1Pick a strategy (size-aware)
2. 2Measure the codebase (code signals)
3. 3Gather process signals (git)
4. 4Categorize & calculate base hours (with ranges)
5. 5Cross-checks (three independent sanity checks)
6. 6Overhead multipliers (compounding, no double-count)
7. 7Market rates
8. 8Organizational overhead → calendar time
9. 9Full team cost
10. 10Claude ROI (session-aware, churn-aware, reviewer-aware, concurrency-aware)
11. 11Sensitivity & cross-validation
12. 12Generate the report

What it can do on your machine

Read from SKILL.md and the folder at commit d8a28a1. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  Ships 6 files in scripts/ (Python and Shell), which the agent can run.

  Shell commands in SKILL.md call:

  • python3
  • bash
  • git

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

• Network

  No URLs in SKILL.md. Its commands use git, which can reach the network depending on how they are called.

  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

Codebase Cost Estimate loads about 5k tokens when it runs, and up to ~11k if it reads all its reference files. Until then it costs about 144 tokens; SKILL.md has 2,294 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~144

When it runs · the whole SKILL.md, loaded when a task matches

~5k

With references · SKILL.md plus every file in references/, read only if the agent opens them

~11k

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

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); the scripts in this folder are not scanned.

SKILL.md

Without a licence we can't republish the file, so here is its outline and opening line. It has 2,294 words (~5,031 tokens).

name

cost-estimate

Read the full SKILL.md on GitHub

Files

SKILL.md and 17 other files (scripts, references, assets) in .claude/skills/cost-estimate of jbarbier/claude-code-cost-estimate.

• SKILL.md
• assets/artifact-schema.json
• assets/report-template.md
• references/category-rates.md
• references/claude-roi.md
• references/cocomo-ii.md
• references/cross-validation.md
• references/function-points.md
• references/locomo.md
• references/market-rates.md
• references/overhead-multipliers.md
• references/team-cost.md
• scripts/claude_token_cost.py
• scripts/compute_dryness.py
• scripts/count_loc.sh
• scripts/git_session_clustering.py
• scripts/git_signals.sh
• scripts/resolve_outdir.py

Open the folder on GitHubat commit d8a28a1