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.
npx skills add nataliacorrea03/claude-code-skills --skill build-capturegit clone --depth 1 https://github.com/nataliacorrea03/claude-code-skillsWrote 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/skills/nataliacorrea03/claude-code-skills/build-capture)<a href="https://agentmods.dev/skills/nataliacorrea03/claude-code-skills/build-capture"><img src="https://agentmods.dev/badge/skills/nataliacorrea03/claude-code-skills/build-capture/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/skills/nataliacorrea03/claude-code-skills/build-capture"><img src="https://agentmods.dev/badge/skills/nataliacorrea03/claude-code-skills/build-capture.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 | $0.00080 | $0.00525 |
| Opus 5 | $0.00040 | $0.00262 |
| Sonnet 5 | $0.00016 | $0.00105 |
| Haiku 4.5 | $0.00008 | $0.00052 |
Grade A, and why
build-capture 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 10d 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.
What it actually says
build-capture
The stuff you build in Claude Code never gets written down unless you stop and do it. You won't. This does it for you.
Once a day a cron reads that day's Claude Code sessions plus the files that changed in a folder you watch, figures out what you actually built or shipped, and appends a short entry for each to a markdown file. Hands-off. Routine chatter and pure Q&A are skipped.
What you get, per build
- Name — short title of the thing you built
- What it is — one plain sentence
- Latest — what happened today (built, shipped, fixed, refactored)
- Type (skill / script / app / fix) + date
Setup (2 minutes)
- Requires the
claudeCLI on your PATH and Python 3. - Set
WATCH_DIRto the folder you build in (default: the current repo /~/.claude/skills), andLOG_FILEfor the log (default~/build-log.md). - Install the daily cron:
(On Linux, use thecp com.example.build-capture-daily.plist ~/Library/LaunchAgents/ # edit the path inside to point at this folder, then: launchctl load ~/Library/LaunchAgents/com.example.build-capture-daily.plistcrontabline indaily-sweep.sh's header.)
Run it by hand
./daily-sweep.sh # log today's builds now
./daily-sweep.sh dry # print what it would log, write nothing
How it works
build_digest.py (pure local, no LLM) collects the last day's session text, the files that changed under WATCH_DIR, and recent git commits, into one digest. A headless claude pass reads it per SWEEP_PROMPT.md and appends the builds to your log, deduping by name so re-runs don't pile up. Additive only, it never edits past entries.
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 10d ago First seen · 37 lines · 80 tokens per session scan A fd49125cb968
build-capture is a skill published in the GitHub repository nataliacorrea03/claude-code-skills (4 stars, last pushed 1mo ago), licensed MIT. It adds 80 tokens to every session and 525 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
notebooklm-manager
Manages NotebookLM notebooks — query, add, list, search, enable/disable, remove. Use when a notebooklm.google.com URL appears or user mentions NotebookLM. Handles URLs through its own Chrome agent — do not navigate directly. Requires: claude-in-chrome MCP.
lx
Codebase exploration tool that reads many files or whole directories in a single call, with per-file headers, glob include/exclude filters, function/type skeleton extraction (signatures only, no bodies), and head/tail line slicing.
find-plugin-file
This skill should be used when needing to locate files within the Claude Code plugins cache directory (/.claude/plugins/cache). Triggers include finding tool scripts, skill files, or any plugin resource when the hardcoded path is unknown or varies by plugin version. Use when slash commands or orchestrators need to…
flow-lean
Use when the user explicitly asks for Flow Lean, lean or less verbose output, action-first responses, expansion of a compressed Flow Lean answer, or Flow Lean recap and skills-footer controls.
morning-triage
Discovery for an autonomous loop — find this turn's work instead of being handed it. Reads what changed since the last run (failed CI, new issues, merged commits), judges what's actually worth acting on, writes findings to a durable state file, and hands each off to the SDLC loop with a stop-condition. Use as the…
eco-max
Maximum-savings variant of /eco - the same frugality rules PLUS a low reasoning-effort override for the invoked task. Use for routine chores (rename, small fix, quick question, boilerplate) when the user wants absolute minimum token spend; prefer plain /eco for hard or high-stakes work. Works in any language.