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 OKHP3/skillz --skill codebase-discoverygit clone --depth 1 https://github.com/OKHP3/skillzWrote 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/okhp3/skillz/codebase-discovery)<a href="https://agentmods.dev/skills/okhp3/skillz/codebase-discovery"><img src="https://agentmods.dev/badge/skills/okhp3/skillz/codebase-discovery/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/okhp3/skillz/codebase-discovery"><img src="https://agentmods.dev/badge/skills/okhp3/skillz/codebase-discovery.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 | $0.00108 | $0.02502 |
| Opus 5 | $0.00054 | $0.01251 |
| Sonnet 5 | $0.00022 | $0.00500 |
| Haiku 4.5 | $0.00011 | $0.00250 |
Grade A, and why
codebase-discovery 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 6d 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 — 207 lines — stays where its author put it; the contents beside it link to each section on GitHub.
User Input
$ARGUMENTS
You MUST consider the user input before proceeding (if not empty). It identifies the codebase (or subsystem) to analyse and, optionally, the mode.
Purpose
Reverse-engineer enough business and domain knowledge out of an existing codebase to onboard a new team member — human or AI — and to give AI harness tooling (e.g. Spec Kit) the context it needs before any specification or change work begins.
The output is a small, lean set of onboarding documents under docs/, not a
comprehensive knowledge base. Each document is written so it can be linked from a
CLAUDE.md / AGENTS.md without consuming an unreasonable amount of context.
This skill is the orchestrator. It runs five phases, each defined in its own playbook
under playbooks/. Read and follow the relevant playbook at each phase.
Core principle
The code is ground truth for what the system does. Only people hold the why.
So the method is: mine the code first to form evidence-backed hypotheses, then spend the human's time validating intent and explaining, not re-deriving mechanics. Existing docs (README, CLAUDE.md, AGENTS.md, wikis) are a valuable starting point, but because documentation naturally drifts from code over time, the source code is the source of truth — everything is verified against it before being relied on.
Roles
Adopt the role that fits the phase:
- Recon / synthesis: act as a Senior Software Engineer + Solution Architect reading the system as-is. Understanding existing architecture is in scope; designing new architecture or proposing changes is not, unless explicitly asked.
- Interview: act as a Senior Business Analyst supported by a Product Manager. Understand business intent, users, rules and domain language.
Modes
Determine the mode from the user input (default to full and confirm):
- full — Pre-check → Recon → Interview → Synthesis → Verify. Requires a stakeholder (senior BA / Product Owner / SME) to validate findings.
- code-only — Pre-check → Recon → Synthesis → Verify, with no interview.
Everything that would need human confirmation is emitted as
[assumption]/[unverified]for later validation. Use when no SME is available yet.
What ships with it
27 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.
- playbooks/00-pre-check.md 3.2 KB
- playbooks/01-deep-recon.md 6.8 KB
- playbooks/02-interview.md 3.9 KB
- playbooks/03-synthesis.md 6.0 KB
- playbooks/04-verification.md 2.6 KB
- README.md 5.8 KB
- references/code-intelligence.md 4.7 KB
- references/lsp-mcp/claude-code.mcp.json 601 B
- references/lsp-mcp/config.yaml 1.2 KB
- references/output-conventions.md 3.9 KB
- references/provenance-and-status.md 2.9 KB
- references/question-bank.md 3.3 KB
- references/recon-heuristics.md 3.9 KB
- templates/agent-onboarding-file.md 1.6 KB
- templates/assumptions-register.md 854 B
- templates/business-requirements.md 1.4 KB
- templates/business-rules.md 933 B
- templates/current-architecture.md 1.2 KB
- templates/discovery-state.md 1.1 KB
- templates/domain-glossary.md 741 B
- templates/domain-model.md 994 B
- templates/integrations.md 988 B
- templates/project-readme.md 2.0 KB
- templates/recon-manifest.md 1018 B
- templates/traceability-index.md 590 B
- templates/user-personas.md 815 B
- templates/workflows.md 939 B
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.
- 6d ago First seen · 207 lines · 108 tokens per session scan A ab813652857a
codebase-discovery is a skill published in the GitHub repository OKHP3/skillz (3 stars, last pushed yesterday), licensed MIT. It adds 108 tokens to every session and 2,502 once invoked, about $0.0005 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 2026-09-03.
Other skills, from other repositories
baoyu-comic
A tool for creating original educational comics that explain knowledge or ideas through multiple illustrated panels. It supports different art styles and tones and can create several comics in one batch.
pm-career-coach
PM Career Coach — guides product managers through career transitions, skill development, and growth planning Use when: Planning your PM career path, preparing for promotion, navigating role transitions, or seeking career advice.
pm-interview-prep
PM Interview Preparation — practice product sense, execution, behavioral, and strategy questions Use when: Preparing for PM job interviews, practicing case studies, or refining interview responses.
kelly-homework-coach
A child-friendly homework coaching desk for elementary students. It explains photographed or pasted questions, studies wrong answers, keeps a mistake notebook, and prepares practice papers for review.
kelly-lesson
A lesson-planning and compliance desk for schools or training programs. It drafts plans from curriculum materials and a required template, checks them against set standards, and routes them for review.
kelly-education-intel
A daily research workspace for the education industry, including training centres, tutoring, exams, study abroad, visas, and admissions. It collects source-backed signals, explains their relevance, and prepares possible actions and draft messages for review.