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 thienhoc/dwi-by-thienhoc --skill dwi-leangit clone --depth 1 https://github.com/thienhoc/dwi-by-thienhocWrote 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/thienhoc/dwi-by-thienhoc/dwi-lean)<a href="https://agentmods.dev/skills/thienhoc/dwi-by-thienhoc/dwi-lean"><img src="https://agentmods.dev/badge/skills/thienhoc/dwi-by-thienhoc/dwi-lean/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/thienhoc/dwi-by-thienhoc/dwi-lean"><img src="https://agentmods.dev/badge/skills/thienhoc/dwi-by-thienhoc/dwi-lean.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 | $0.00055 | $0.00529 |
| Opus 5 | $0.00028 | $0.00264 |
| Sonnet 5 | $0.00011 | $0.00106 |
| Haiku 4.5 | $0.00006 | $0.00053 |
Grade A, and why
dwi-lean 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 10d 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 — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Dwi Lean
Find the smallest sufficient path from the requested outcome to credible evidence, then stop.
First principle
Do not optimize the process before understanding the finish line.
Name:
- the requested outcome;
- the allowed scope;
- the acceptance condition;
- the evidence needed;
- the actions that are explicitly out of scope.
If these are already clear, do not ask the person to repeat them.
Choose the work shape
Direct
Use for a small, reversible, well-specified change. Act without a formal plan.
Bounded plan
Use when several dependent steps or files are involved. Keep the plan short and outcome-based.
Risk-controlled
Use only when architecture, migration, concurrency, security, irreversible effects, cross-repository work, or ambiguous authority is genuinely present. Narrow the risky part instead of inflating the whole task.
Execution protocol
- Read only the files needed to identify the change.
- Prefer one coherent edit over many exploratory edits.
- Reuse existing conventions before introducing a new abstraction.
- Add no dependency, service, agent, or governance artifact without demonstrated need.
- Keep optional enhancements separate from the requested outcome.
- If a new uncertainty appears, pause only the affected step.
Proportionate evidence
Match checking effort to the claim:
- Text or metadata change: inspect structure and links.
- Local behavior change: run the narrowest relevant check.
- Shared contract change: run contract and focused regression checks.
- High-risk or release claim: use independent evidence appropriate to the risk.
Do not run a broad test campaign merely because tools are available. Do not claim completion without the evidence the finish line requires.
Anti-expansion checks
Before adding work, ask:
- Does this change the requested outcome?
- Does current evidence show the need?
- Is there a smaller reversible way?
- Is this a required gate or only a preference?
- Can it become a clearly labeled next step instead?
What ships with it
1 file 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.
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.
- 10d ago First seen · 73 lines · 55 tokens per session scan A 4b4d59ff5a12
dwi-lean is a skill published in the GitHub repository thienhoc/dwi-by-thienhoc (3 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 55 tokens to every session and 529 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 2026-08-31.
Other skills, from other repositories
awsl
Run Claude Code JavaScript Workflows through the awsl compatibility runtime. Use when an agent's current task or loaded Skill requires dispatching a Claude Code Workflow but the host cannot execute that Workflow natively, or when awsl workflow inspection, durable run state, resume, or provider diagnostics are needed.
handoff
Compress project context into HANDOFF.md with workflow state, analysis checkpoint, next gate, verification, current hypothesis, freshness anchors, optional gotcha references, and a resume packet for the next agent session.
grill-with-docs-lite
Groom a fuzzy request and the smallest relevant source set into a bounded PRE-SPEC ASSEMBLY packet for mini-spec, separating evidence from decisions, assumptions, and blockers before contract language is written.
analyze-mini
Risk-triggered consistency checkpoint that detects when task artifacts, assumptions, or verification no longer support a safe build decision.
ceremony-budget
Choose the smallest workflow that still buys back enough attention and safety for the task.
teach-back
Transfer ownership of a verified implementation by testing and repairing the human's understanding of its behavior, decisions, and failure modes without turning every task into a tutorial.