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 agentmods add skills/helderberto/agent-skills/source-drivennpx skills add helderberto/agent-skills --skill source-drivengit clone --depth 1 https://github.com/helderberto/agent-skillsWhat 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 | $0.00059 | $0.00400 |
| Opus 5 | $0.00030 | $0.00200 |
| Sonnet 5 | $0.00012 | $0.00080 |
| Haiku 4.5 | $0.00006 | $0.00040 |
Grade A, and why
source-driven 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 2d 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
Source-Driven Development
Never rely on training data for API usage. Read the actual source of truth.
Workflow
1. Identify Dependencies
- Read
package.json(or equivalent manifest) for exact versions - Note the exact version of each library involved in the task
2. Fetch Official Docs
For each dependency involved:
- Find the correct docs URL for that specific version (not "latest")
- Fetch the relevant API page using WebFetch
- Extract: function signatures, required params, return types, breaking changes
If docs are unavailable or ambiguous, read the library source in node_modules/.
3. Implement from Docs
- Use only APIs confirmed in fetched docs
- Match function signatures exactly (param order, types, defaults)
- If a doc page confirms the API: proceed
- If you cannot verify an API: mark it
// UNVERIFIED: could not confirm in docs for v{version}
4. Cite Sources
Add a brief comment on non-obvious API usage:
// Ref: https://docs.example.com/v3/api#method
Only cite when the usage is surprising or version-specific. Don't over-comment obvious calls.
Error Handling
- Docs URL returns 404 → try GitHub repo README, then
node_modules/source - Version not found in docs → use closest version docs + mark
// UNVERIFIED: docs for v{closest}, installed v{actual} - WebFetch blocked/unavailable → read
node_modules/{pkg}/README.mdor type definitions
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.
- 2d ago First seen · 49 lines · 59 tokens per session scan A 2ce9de01265b
source-driven is a skill published in the GitHub repository helderberto/agent-skills (13 stars, last pushed 11d ago), licensed MIT. It adds 59 tokens to every session and 400 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
code-review-and-quality
Conducts multi-axis code review. Use before merging any change. Use when reviewing code written by yourself, another agent, or a human. Use when you need to assess code quality across multiple dimensions before it enters the main branch.
constraint-driven-development
Establishes a project's quality bar as a written contract and stops agents quietly lowering it. Interviews the user on which dimensions matter, supplies sane default thresholds when they have no number in mind, records everything in CONSTRAINTS.md, and watches the diff for a weakened bar — new @ts-ignore or…
performance-optimization
Optimizes application performance across frontend, backend, queries, and databases. Use when performance requirements exist, when you suspect performance regressions, when Core Web Vitals or load times need improvement, when N+1 query patterns need fixing, or when profiling reveals bottlenecks.
api-and-interface-design
Guides stable API and interface design. Use when designing APIs, module boundaries, or any public interface. Use when creating REST or GraphQL endpoints, defining type contracts between modules, or establishing boundaries between frontend and backend.
code-simplification
Simplifies code for clarity. Use when refactoring code for clarity without changing behavior. Use when code works but is harder to read, maintain, or extend than it should be. Use when reviewing code that has accumulated unnecessary complexity.
doubt-driven-development
Subjects every non-trivial decision to a fresh-context adversarial review before it stands. Use when correctness matters more than speed, when working in unfamiliar code, when stakes are high (production, security-sensitive logic, irreversible operations), or any time a confident output would be cheaper to verify now…