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 juliusz-cwiakalski/agentic-delivery-os --skill write-decisiongit clone --depth 1 https://github.com/juliusz-cwiakalski/agentic-delivery-osWrote 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/juliusz-cwiakalski/agentic-delivery-os/write-decision)<a href="https://agentmods.dev/skills/juliusz-cwiakalski/agentic-delivery-os/write-decision"><img src="https://agentmods.dev/badge/skills/juliusz-cwiakalski/agentic-delivery-os/write-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/juliusz-cwiakalski/agentic-delivery-os/write-decision"><img src="https://agentmods.dev/badge/skills/juliusz-cwiakalski/agentic-delivery-os/write-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 | $0.00031 | $0.04884 |
| Opus 5 | $0.00015 | $0.02442 |
| Sonnet 5 | $0.00006 | $0.00977 |
| Haiku 4.5 | $0.00003 | $0.00488 |
Grade A, and why
write-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 12d 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 — 252 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Renders the record proportionally by rigor (R1 compact subset / R2 standard / R3 full), records AI-assistance provenance, and keeps R2/R3 records in a PR-reviewed flow: Proposed on the branch, Accepted when merged to main.
User invocation: /write-decision
Inputs other than MUST be sourced from the active decision planning context (especially the accepted <decision_planning_summary> or <technical_decision_planning_summary> block and their accepted generic or adr.* fields) and relevant repository docs; NOTHING may be invented.
The resulting decision record becomes the canonical record of the decision and its rationale, and should be linked from related changes and specs.
<directory_rules>
- Normalize number: strip non-digits; pad left with '0' to length 4.
- groupFolder is NOT used; all decision records live directly under
doc/decisions/. - decisionType defaults to ADR; may be overridden to PDR, TDR, BDR, or ODR based on planning context or user input.
- slug = normalized-from-title (lowercase ASCII kebab-case, <=60 chars), derived from the decision title.
- filename = --.md (e.g., ADR-0001-event-bus.md, TDR-0001-state-mgmt.md)
- fullPath = doc/decisions/--.md </directory_rules>
<front_matter_rules> A YAML front matter block MUST precede the decision record body and include at least these keys:
id: - # e.g., ADR-0001, PDR-0001, TDR-0001 decision_type: <adr|pdr|tdr|bdr|odr> created: # UTC date when file is first created decision_date: null | # Date when status changed to Accepted review_date: null | # Next retrospective/review date; set on Acceptance last_updated: # UTC date of last modification status: <Proposed|Accepted|Deprecated|Superseded> summary: owners: [] service: <primary impacted service, system, or domain> links: related_changes: ["PDEV-123", ...] supersedes: ["-####", ...] superseded_by: ["-####", ...] spec: ["doc/spec/...", ...] contracts: ["doc/contracts/...", ...] diagrams: ["doc/diagrams/...", ...] decisions: ["-####", ...] # other relevant decision records
Validation:
- Status lifecycle is
Proposed → Accepted → (Deprecated | Superseded). - id MUST be exactly
<TYPE>-<number>where TYPE is ADR/PDR/TDR/BDR/ODR and is the zero-padded string form. - decision_type MUST be one of: adr, pdr, tdr, bdr, odr (lowercase).
- created and last_updated MUST be valid dates in ISO format YYYY-MM-DD (UTC calendar date).
- On first creation:
- status MUST be "Proposed" because branch records are pre-merge drafts.
- records merged to main SHOULD be "Accepted".
- when status becomes Accepted, set decision_date and review_date.
- owners MUST contain at least one entry (e.g., a team or person handle).
- related_changes MAY be empty; when present, values MUST be valid workItemRef identifiers (e.g.,
PDEV-123,GH-456). - Additional front-matter fields allowed by doc/documentation-handbook.md (e.g., tags, security) MAY be added but MUST NOT replace the keys above. </front_matter_rules>
<context_lookup> The decision record generator must base its content on:
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.
- 12d ago First seen · 252 lines · 31 tokens per session scan A 5240ab893bc7
write-decision is a skill published in the GitHub repository juliusz-cwiakalski/agentic-delivery-os (38 stars, last pushed 2d ago), licensed MIT. It adds 31 tokens to every session and 4,884 once invoked, about $0.0002 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
Verification & Quality Assurance
Comprehensive truth scoring, code quality verification, and automatic rollback system with 0.95 accuracy threshold for ensuring high-quality agent outputs and codebase reliability.
agent-github-modes
Agent skill for github-modes - invoke with $agent-github-modes.
workflow-automation
Workflow creation, execution, and template management. Automates complex multi-step processes with agent coordination. Use when: automating processes, creating reusable workflows, orchestrating multi-step tasks. Skip when: simple single-step tasks, ad-hoc operations.
deployment-pipeline-design
Design multi-stage CI/CD pipelines with approval gates, security checks, and deployment orchestration. Use this skill when designing zero-downtime deployment pipelines, implementing canary rollout strategies, setting up multi-environment promotion workflows, or debugging failed deployment gates in CI/CD.
gitlab-ci-patterns
Build GitLab CI/CD pipelines with multi-stage workflows, caching, and distributed runners for scalable automation. Use when implementing GitLab CI/CD, optimizing pipeline performance, or setting up automated testing and deployment.
bazel-build-optimization
Optimize Bazel builds for large-scale monorepos. Use when configuring Bazel, implementing remote execution, or optimizing build performance for enterprise codebases.