Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

A5c AI/Codebase Research — measured AI agent skill | DecimalAI

a5c-ai/codebase-research

SkillScore82Maintained

Systematic codebase exploration following the Iron Law - understand the problem before exploring code. Four phases with file-finder and web-researcher agents.

by a5c-ai

Links this skill to your agents and keeps it current with the author’s updates.

Automatic

Coding pack

decimalai skills pull a5c-ai-codebase-research

Get this skill — curl · raw file

curl -fsSL https://app.decimal.ai/s/a5c-ai-codebase-research/SKILL.md

Raw file: /s/a5c-ai-codebase-research/SKILL.md ↗ · machine-readable summary at /s/a5c-ai-codebase-research.json ↗

In productionGlobal

how this skill behaves on real traffic · last 30 days

No production data for this skill yet — usage numbers appear here once agents start running it.

Anonymized aggregate across every org using this skill — proof from real production use, not a demo.

Does this skill help? · Benchmark: with vs. withoutsign in to run this on your agents

22 test cases from the publisher’s eval.yaml · each run twice on gemini-3.6-flash — with the skill injected, then without · last run 9d ago

—-32% tokens0% turns82% of whole cases pass with skill (18/22)

Test case	Without → With	Effect	Δ tokens	Δ turns
case-01	✗→✓	▲ Improved	1%	0%
case-02	✗→✓	▲ Improved	-73%	0%
case-03	✗→✓	▲ Improved	-52%	0%
case-04	✗→✓	▲ Improved	52%	0%
case-05	✗→✓	▲ Improved	39%	0%

Showing 5 of 22 cases

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 7/31/2026

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

a5c-ai / babysitter

library/methodologies/rpikit/skills/codebase-research/SKILL.md

View on GitHub ↗

License MITImported 7/31/2026Version v1

Skill contents

SKILL.md

Investigating how an existing feature works before modifying it
Understanding dependencies and data flows before planning
Gathering context for a known goal

Process

Understand the request - Ask clarifying questions one at a time (purpose, specifics, scope, constraints, context). Do NOT read any files until confirmed.
Explore the codebase - Use file-finder agent, read in order, trace data flows, identify constraints.
Document findings - Write structured research document to docs/plans/YYYY-MM-DD-<topic>-research.md.
Transition - Ask: plan, continue research, or conclude.

Key Rules

Quotations from source material capped at 125 characters maximum
Only proceed to exploration after human confirms understanding
Use file-finder agent for initial file discovery
Use web-researcher agent for external context needs

Agents Used

agents/file-finder/ - Locates relevant files with suggested reading order
agents/web-researcher/ - Gathers external context when needed

Tool Use

Invoke via babysitter process: methodologies/rpikit/rpikit-research

Want to see if a5c-ai/codebase-research would activate on your phrasing? Try it before you install — no LLM call, no signup.

Other measured skills in the registry, with their headline benchmark lift.