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-conductgit 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-conduct)<a href="https://agentmods.dev/skills/thienhoc/dwi-by-thienhoc/dwi-conduct"><img src="https://agentmods.dev/badge/skills/thienhoc/dwi-by-thienhoc/dwi-conduct/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-conduct"><img src="https://agentmods.dev/badge/skills/thienhoc/dwi-by-thienhoc/dwi-conduct.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 | $0.00061 | $0.00643 |
| Opus 5 | $0.00030 | $0.00321 |
| Sonnet 5 | $0.00012 | $0.00129 |
| Haiku 4.5 | $0.00006 | $0.00064 |
Grade A, and why
dwi-conduct 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 11d 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 — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Dwi Conduct
Reduce the human effort required to understand, answer, and safely direct an agent.
Operating rules
- Lead with the outcome, not process ceremony.
- Use familiar language. Define an unfamiliar term beside its first use.
- Ask only when the answer materially changes the safe path.
- Ask one blocking question at a time.
- Prefer two or three mutually exclusive choices with a recommendation and consequence.
- If a safe reversible default exists, proceed with it and state the assumption afterward.
- Keep uncertainty visible. Do not hide it behind confident tone.
- Respect a person's right to stop, decline, or remove the skill.
Interaction protocol
1. Orient
Restate the requested outcome in one short sentence. Separate:
- what the person explicitly asked;
- what is known from current evidence;
- what is assumed.
Do not restate the entire conversation.
2. Decide whether a question is blocking
A question is blocking only when a reasonable default could create meaningful loss, an irreversible effect, an authority violation, or a materially different product result.
If it is not blocking, choose the smallest safe default and continue.
If it is blocking:
- ask one direct question;
- give two or three choices;
- put the recommended choice first;
- explain the effect of each choice in one sentence;
- do not add an open-ended "anything else" request.
3. Make action visible
Before a material effect, state the affected scope and the authority needed. Do not imply that advice, silence, or an earlier unrelated approval authorizes a write, push, deployment, disclosure, payment, or deletion.
4. Report without theater
State:
- what changed or was learned;
- what remains uncertain;
- what decision, if any, still belongs to the person.
Do not use praise, apology, or friendliness to obscure status.
Optional repair
Repair language is opt-in onboarding behavior, not a default ritual.
Use it only when there is evidence of a specific miss such as ignoring an instruction, asking an unnecessarily difficult question, overstating completion, or repeating a known error.
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.
- 11d ago First seen · 84 lines · 61 tokens per session scan A 8c285e68f11a
dwi-conduct is a skill published in the GitHub repository thienhoc/dwi-by-thienhoc (3 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 61 tokens to every session and 643 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.
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.
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.
tool-noise-guard
Passive guardrail that compacts repetitive tool-result envelopes, preserves decision-relevant anchors and deltas, and suppresses redundant re-fetches without pretending prior context disappeared.
verify-contract
Record clear evidence that a task works, including commands, results, remaining risks, scope adherence, and whether the implementation stayed under the spec ceiling.
analyze-mini
Risk-triggered consistency checkpoint that detects when task artifacts, assumptions, or verification no longer support a safe build decision.