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 davekilleen/Dex --skill feature-decisiongit clone --depth 1 https://github.com/davekilleen/DexWrote 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/davekilleen/dex/feature-decision)<a href="https://agentmods.dev/skills/davekilleen/dex/feature-decision"><img src="https://agentmods.dev/badge/skills/davekilleen/dex/feature-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/davekilleen/dex/feature-decision"><img src="https://agentmods.dev/badge/skills/davekilleen/dex/feature-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 | $0.00011 | $0.02849 |
| Opus 5.5 | $0.00004 | $0.01140 |
| Sonnet 5.5 | $0.00002 | $0.00570 |
| Haiku 4.5 | $0.00001 | $0.00285 |
Grade A, and why
feature-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 1mo 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 — 383 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Purpose
Make and document feature prioritization decisions with a structured framework. Ensures key factors are considered, stakeholders are consulted, and rationale is preserved for future reference.
Evidence, authority, and recovery
Treat this skill as decision support: a recommendation is analysis, while the decision belongs to an identified human authority.
- Attach a source ID or path, source date, and as-of date to every material claim, quote, estimate, stakeholder input, and roadmap fact. Keep the evidence date separate from the date the human confirms a decision.
- Expose unknown effort and unknown evidence as first-class values.
Unknowneffort is not Small, and missing evidence is not evidence of no impact; name the missing input or assumption instead of choosing a convenient rating. Preserve contradictory evidence with both sources and dates rather than reconciling it silently. - Never invent absent customer names, user counts, revenue, effort estimates, dates, stakeholder alignment, owners, quotes, or dependencies. If a field is not supported, record
unknownornot providedand explain what would resolve it. - Keep the recommendation separate from the decision authority: label the output
RecommendationandHuman decision authorityseparately. Recommendations are not human decisions; only the human authority may choose or confirm Go, No-Go, or Defer. - Before creating or updating a decision document, search for existing decisions for the feature and show an exact preview: target path, create/update operation, and complete proposed contents or diff. Require explicit confirmation from the human authority before any change.
- Preserve each earlier decision. Never overwrite it silently: append a dated decision entry when extending the record, or explicitly supersede the earlier decision with the human authority, reason, and link recorded.
- After an approved write, read back the target and compare it with the confirmed preview. If the write fails or the read-back differs, report the exact failure, leave the earlier decision intact, do not claim the document was created or updated, and recover by re-reading the current file and presenting a new preview for explicit confirmation.
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.
- 1mo ago First seen · 383 lines · 11 tokens per session scan A 29d3c5d0007f
feature-decision is a skill published in the GitHub repository davekilleen/Dex (508 stars, last pushed yesterday), licensed MIT. It adds 11 tokens to every session and 2,849 once invoked, about $0.0000 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 2026-09-02.
Other skills, from other repositories
parallel-feature-development
Coordinate parallel feature development with file ownership strategies, conflict avoidance rules, and integration patterns for multi-agent implementation. Use this skill when decomposing a large feature into independent work streams, when two or more agents need to implement different layers of the same system…
saga-orchestration
Implement saga patterns for distributed transactions and cross-aggregate workflows. Use this skill when implementing distributed transactions across microservices where 2PC is unavailable, designing compensating actions for failed order workflows that span inventory, payment, and shipping services, building…
task-coordination-strategies
Decompose complex tasks, design dependency graphs, and coordinate multi-agent work with proper task descriptions and workload balancing. Use this skill when breaking down work for agent teams, managing task dependencies, or monitoring team progress.
bazel-build-optimization
Optimize Bazel builds for large-scale monorepos. Use when configuring Bazel, implementing remote execution, or optimizing build performance for enterprise codebases.
nx-workspace-patterns
Configure and optimize Nx monorepo workspaces. Use when setting up Nx, configuring project boundaries, optimizing build caching, or implementing affected commands.
context-driven-development
Creates and maintains project context artifacts (product.md, tech-stack.md, workflow.md, tracks.md) in a conductor/ directory. Scaffolds new projects from scratch, extracts context from existing codebases, validates artifact consistency before implementation, and synchronizes documents as the project evolves. Use when…