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 sohaibt/product-mode --skill decisiongit clone --depth 1 https://github.com/sohaibt/product-modeWrote 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/sohaibt/product-mode/decision)<a href="https://agentmods.dev/skills/sohaibt/product-mode/decision"><img src="https://agentmods.dev/badge/skills/sohaibt/product-mode/decision/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/sohaibt/product-mode/decision"><img src="https://agentmods.dev/badge/skills/sohaibt/product-mode/decision.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 | $0.00034 | $0.00446 |
| Opus 5.5 | $0.00014 | $0.00178 |
| Sonnet 5.5 | $0.00007 | $0.00089 |
| Haiku 4.5 | $0.00003 | $0.00045 |
Grade A, and why
decision 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 today.
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
Decision record
Record the decision the user names. Use the text after the command as the decision title. If there is no text, use the most recent non-trivial decision in the conversation, and confirm the title with the user.
- Check
.product-mode/decisions/for an entry about the same decision. If one exists, update it instead of writing a new one, and tell the user its path. - Draft each field from the conversation and the code:
- Context: the problem and the constraints
- Options considered: every option that was discussed, including the rejected ones
- Choice: the option chosen, and the reason
- Reversibility:
one-way doorortwo-way door - Revisit trigger: the metric, date, or condition that reopens this decision
- Never invent options, reasons, or evidence that the conversation does not contain. If the reason or the revisit trigger is missing, ask for it.
- If the decision is a one-way door (public API, data schema, pricing, brand, core UX), confirm that the user signed off and that the tradeoffs are written down.
- Show the draft. When the user confirms, save the file as
.product-mode/decisions/<UTC timestamp>-<title-slug>.md. Use the timestamp format2026-01-31T09-05-00-000Zand a lowercase, hyphenated slug. Use this content:
## Decision: <title>
Date: <YYYY-MM-DD>
Context: <context>
Options considered: [<A>, <B>, <C>]
Choice: <X>, because <reason>
Reversibility: <one-way door | two-way door>
Revisit trigger: <trigger>
---
*Generated by product-mode /decision*
- Tell the user the saved path.
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.
- today First seen · 36 lines · 34 tokens per session scan A 5862328f8f96
decision is a skill published in the GitHub repository sohaibt/product-mode (176 stars, last pushed yesterday), licensed MIT. It adds 34 tokens to every session and 446 once invoked, about $0.0001 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 2026-11-08.
decision compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| decisionsohaibt/product-mode | Skill | 176 | yesterday | MIT | A | 34 | Claude Code |
| dependency-auditornariatrip191/my-claude-skills | Skill | 1 | 28d ago | none | A | 7 | Claude Code, Codex |
| pr-review-expertnariatrip191/my-claude-skills | Skill | 1 | 28d ago | none | A | 8 | Claude Code, Codex |
| skill-security-auditornariatrip191/my-claude-skills | Skill | 1 | 28d ago | none | A | 161 | Claude Code, Codex |
| performance-profilernariatrip191/my-claude-skills | Skill | 1 | 28d ago | none | A | 7 | Claude Code, Codex |
| ci-cd-pipeline-buildernariatrip191/my-claude-skills | Skill | 1 | 28d ago | none | A | 11 | Claude Code, Codex |
| tech-debt-trackernariatrip191/my-claude-skills | Skill | 1 | 28d ago | none | A | 63 | Claude Code, Codex |