Borrowing it
Nothing to install: this file belongs to marcoemrich/agentic_coding_lab. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/marcoemrich/agentic_coding_lab/main/.claude/skills/build-overview/SKILL.mdgit clone --depth 1 https://github.com/marcoemrich/agentic_coding_labWrote 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/marcoemrich/agentic_coding_lab/build-overview)<a href="https://agentmods.dev/skills/marcoemrich/agentic_coding_lab/build-overview"><img src="https://agentmods.dev/badge/skills/marcoemrich/agentic_coding_lab/build-overview/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/marcoemrich/agentic_coding_lab/build-overview"><img src="https://agentmods.dev/badge/skills/marcoemrich/agentic_coding_lab/build-overview.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 4 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Anti-Refusal · line 43 Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak preamble.Fix: Remove instructions that suppress warnings, disclaimers, or ethical commentary. Let the agent surface safety-relevant caveats to the user.
- high Prompt Injection · line 73 Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.
- medium Excessive Agency · line 99 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 135 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00036 | $0.06135 |
| Opus 5.5 | $0.00014 | $0.02454 |
| Sonnet 5.5 | $0.00007 | $0.01227 |
| Haiku 4.5 | $0.00004 | $0.00613 |
Grade A, and why
build-overview 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 25d 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.
How it starts
The opening of the file, as written. The whole thing — 225 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/build-overview — produce an experiment-overview snapshot
You produce a frozen, publishable research report from the current state of every findings.md under research/questions-claude/, research/questions-opencode/, research/questions-cross/, and research/workflow-dev/. The snapshot lands as a new file under research/reports/experiment-overview-YYYY-MM-DD.md.
Core principle
findings.md = living document, growing list of status-tagged findings.
Snapshot = frozen, table-heavy report at a point in time.
Both exist in parallel. The snapshot is not written from memory — it is filled in from an auto-generated skeleton.
Prerequisites
Required on $PATH for the Markdown snapshot (steps 1–5):
python3— runsexperiments/generate-snapshot-skeleton.py
Only needed when the user asks for a PDF (step 6):
pandoc— Markdown → HTML (any version ≥ 2.9 works)google-chrome(orchromium— adjust the binary name in step 6) — headless--print-to-pdfpdfinfo(Poppler utils) — optional, used for the PDF verification check
If a PDF was requested and one of its tools is missing, finish the Markdown snapshot and report which tool is unavailable so the user can install it — do not treat it as a failure of the whole run.
Lifecycle (6 steps)
Step 1 — generate the skeleton
Bash:
./experiments/generate-snapshot-skeleton.py
Before trusting the output, verify the script sees every RQ subtree. RQ_TREES in generate-snapshot-skeleton.py is a hardcoded list. When a new subtree appears under research/ (a new harness family, a new question class), the script silently omits it — no warning, no error, just a smaller snapshot. Cross-check the RQ count against the filesystem before proceeding:
# every dir with a README.md carrying an `id:` is an RQ
find research -mindepth 2 -maxdepth 2 -name README.md | xargs grep -l '^id:' | wc -l
./experiments/generate-snapshot-skeleton.py 2>&1 | grep 'RQs:'
If the two numbers disagree, add the missing subtree to RQ_TREES and regenerate — do not hand-patch the skeleton. (This bit in 2026-07: questions-pi/ and questions-cursor-cli/ were missing, which would have dropped 3 RQs and 140 runs from the report.)
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.
- 25d ago Changed d6d536a416f1
- 1mo ago Changed 028ede8c8f22
- 1mo ago Changed 476eb0bd19c3
- 1mo ago Changed 924152fe729e
- 2mo ago First seen · 225 lines · 36 tokens per session scan A 1e1b3765ca70
build-overview is a skill published in the GitHub repository marcoemrich/agentic_coding_lab (30 stars, last pushed 5d ago), licensed MIT. It adds 36 tokens to every session and 6,135 once invoked, about $0.0001 per session on Opus 5.5. 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.
build-overview compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| build-overviewmarcoemrich/agentic_coding_lab | Skill | 30 | 5d ago | MIT | A | 36 | Claude Code |
| apify-youtube-transcript-scrapersickn33/agentic-awesome-skills | Skill | 49k | yesterday | MIT | A | 48 | Claude Code |
| foundry-hosted-agent-validationmicrosoft/agent-framework | Skill | 15k | yesterday | MIT | A | 82 | Claude Code, Codex |
| skill-doc-deliverynyldn/claude-octopus | Skill | 4.4k | yesterday | MIT | A | 29 | Claude Code |
| meta-web-to-pdf-briefingopensquilla/opensquilla | Skill | 7.1k | 6d ago | Apache-2.0 | A | 45 | Claude Code, Codex |
| paper-readerhuangkiki/dailypaper-skills | Skill | 1.3k | 4d ago | Apache-2.0 | A | 135 | Claude Code, Codex |
| chat-complex-documentsvellum-ai/vellum-assistant | Skill | 1.5k | 2d ago | MIT | A | 90 | Claude Code, Codex |