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 sananthanarayan/skilldrop --skill codebase-tourgit clone --depth 1 https://github.com/sananthanarayan/skilldropWrote 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/sananthanarayan/skilldrop/codebase-tour)<a href="https://agentmods.dev/skills/sananthanarayan/skilldrop/codebase-tour"><img src="https://agentmods.dev/badge/skills/sananthanarayan/skilldrop/codebase-tour/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/sananthanarayan/skilldrop/codebase-tour"><img src="https://agentmods.dev/badge/skills/sananthanarayan/skilldrop/codebase-tour.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 | $0.00170 | $0.03507 |
| Opus 5.5 | $0.00068 | $0.01403 |
| Sonnet 5.5 | $0.00034 | $0.00701 |
| Haiku 4.5 | $0.00017 | $0.00351 |
Grade A, and why
codebase-tour 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 5d 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.
The source is not reproduced here
A licence we could not identify
The repository carries a LICENSE file, but it is custom or dual enough that GitHub cannot name it and neither can this catalogue. Unknown terms are not permission, so the body is not copied here. Read the licence at the source and decide for yourself.
What ships with it
60 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.
- evals/eval_queries.json 1.1 KB
- evals/evals.json 11 KB
- evals/files/1/.github/workflows/ci.yml.fixture 606 B
- evals/files/1/openapi.yaml 438 B
- evals/files/1/package-lock.json.fixture 115 B
- evals/files/1/package.json.fixture 724 B
- evals/files/1/README.md 294 B
- evals/files/1/src/config.ts 558 B runs code
- evals/files/1/src/domain/shipments/filter.ts 637 B runs code
- evals/files/1/src/domain/shipments/repository.ts 624 B runs code
- evals/files/1/src/errors.ts 260 B runs code
- evals/files/1/src/generated/api-types.ts 216 B runs code
- evals/files/1/src/http/handlers/shipments.ts 1.4 KB runs code
- evals/files/1/src/http/routes.ts 261 B runs code
- evals/files/1/src/jobs/export-shipments.ts 842 B runs code
- evals/files/1/src/server.ts 554 B runs code
- evals/files/1/tests/domain/filter.test.ts 656 B runs code
- evals/files/1/tests/http/shipments.test.ts 713 B runs code
- evals/files/1/tsconfig.json 180 B
- evals/files/1/vitest.config.ts 126 B runs code
- evals/files/2/.github/workflows/ci.yml.fixture 334 B
- evals/files/2/noxfile.py 341 B runs code
- evals/files/2/pyproject.toml.fixture 509 B
- evals/files/2/README.md 318 B
- evals/files/2/src/ledgerline/__init__.py 71 B runs code
- evals/files/2/src/ledgerline/_version.py 173 B runs code
- evals/files/2/src/ledgerline/cli.py 967 B runs code
- evals/files/2/src/ledgerline/detect.py 458 B runs code
- evals/files/2/src/ledgerline/errors.py 123 B runs code
- evals/files/2/src/ledgerline/money.py 506 B runs code
- evals/files/2/src/ledgerline/parsers/__init__.py 239 B runs code
- evals/files/2/src/ledgerline/parsers/acme.py 632 B runs code
- evals/files/2/src/ledgerline/parsers/base.py 498 B runs code
- evals/files/2/src/ledgerline/parsers/harbor.py 510 B runs code
- evals/files/2/tests/fixtures/acme_sample.csv 118 B
- evals/files/2/tests/test_acme.py 697 B runs code
- evals/files/2/tests/test_detect.py 370 B runs code
- evals/files/3/.github/workflows/ci.yml.fixture 694 B
- evals/files/3/cmd/tidepool/main.go 512 B
- evals/files/3/go.mod.fixture 79 B
- evals/files/3/internal/config/config.go 872 B
- evals/files/3/internal/dispatch/dispatcher_test.go 1.1 KB
- evals/files/3/internal/dispatch/dispatcher.go 1.2 KB
- evals/files/3/internal/dispatch/sender.go 750 B
- evals/files/3/internal/replay/replay.go 839 B
- evals/files/3/internal/store/db.go 810 B
- evals/files/3/internal/store/query.sql 382 B
- evals/files/3/internal/store/query.sql.go 884 B
- evals/files/3/internal/store/schema.sql 149 B
- evals/files/3/internal/store/store_integration_test.go 347 B
- evals/files/3/Makefile 240 B
- evals/files/3/README.md 254 B
- evals/files/3/sqlc.yaml 187 B
- evals/files/4/.env.example 144 B
- evals/files/4/.github/workflows/ci.yml.fixture 312 B
- evals/files/4/data/rates.csv 117 B
- evals/files/4/Makefile 375 B
- evals/files/4/pyproject.toml.fixture 397 B
- evals/files/4/README.md 436 B
- evals/files/4/scripts/gen_rates.py 964 B runs code
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.
- 5d ago First seen · 116 lines · 170 tokens per session scan A 873cc8dd5264
codebase-tour is a skill published in the GitHub repository sananthanarayan/skilldrop (2 stars, last pushed today), with no licence file. It adds 170 tokens to every session and 3,507 once invoked, about $0.0007 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 2026-10-21.
Other skills, from other repositories
greek-philosopher
Channel ancient wisdom through Socratic questioning, Stoic principles, and philosophical inquiry to examine life's deepest questions with poetic eloquence and timeless insight. Use when examining a life decision, seeking Stoic perspective on adversity, or wanting Socratic questioning of an assumption.
gym-training-expert
Apply cutting-edge exercise science from 2025 research on hypertrophy, progressive overload, biomechanics, and evidence-based training protocols for optimal strength and muscle development. Use when designing a training program, choosing exercises and progression, or applying evidence-based hypertrophy/strength…
feynman-thinking
Transform Claude into a Feynman mentor. Focuses on simple explanations, architectural models, Socratic questioning, and stripping away unnecessary complexity. Triggers on: feynman, feynman alignment, explain simply, explain architecture, explain logic, explain concept, build mental model.
acos-visual-gen
Generate research-grounded visuals using the InfoGenius pipeline. Use when creating infographics, diagrams, educational visuals, or any image that benefits from factual accuracy. Supports 8 visual styles (3D, technical, minimalist, photorealistic, futuristic, vintage, cartoon, standard) and 4 audience levels.
conflict-resolver
Résolution de conflits entre agents ou sous-agents quand les résultats sont contradictoires, avec workflow de détection, arbitrage, merge et feedback loop. Se déclenche avec "conflit agent", "agent conflict", "résultats contradictoires", "agent disagreement", "contradiction agents", "arbitrage agent", "résoudre…
email-agent-builder
Construction d'agents de gestion d'emails incluant tri, réponse automatique, extraction et classification. Se déclenche avec "email agent", "agent email", "tri automatique", "réponse automatique email", "classification email. Also triggers on "auto reply agent", "inbox triage agent".