agentmods.dev

spec-writer

spec-writer is an agent for Claude Code from juliusz-cwiakalski/agentic-delivery-os. It costs 8 tokens per session (2,210 once invoked), scanned A, original, MIT.

An agent that writes canonical change specifications: documents describing what should change in a project. It uses planning context and repository documentation without writing implementation code or performing Git operations.

In plain words
What is it for?
Use it to create or update a specification for a work item, place it in the required dated folder, and define the change without code-level tasks.
Why use it?
It turns an agreed change into a consistent, trackable specification while keeping implementation and version-control work separate.

Agent for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: model in frontmatter; mentions OpenCode.

Part of the ados plugin — 20 skills, 24 agents shipped together

not rated 37repo 3d ago A scan 8 tokens original MIT

Good fit Use it to create or update a specification for a work item, place it in the required dated folder, and define the change without code-level tasks.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/juliusz-cwiakalski/agentic-delivery-os/spec-writer
View source ↗ juliusz-cwiakalski/agentic-delivery-os
Install

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.

Clone the repo
git clone --depth 1 https://github.com/juliusz-cwiakalski/agentic-delivery-os

Made for: Claude Code.

Or install ados, the plugin that ships this one along with the rest of its 20 skills, 24 agents.

Wrote 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.

agentmods badge for spec-writer

README.md
[![agentmods](https://agentmods.dev/badge/agents/juliusz-cwiakalski/agentic-delivery-os/spec-writer/github.svg)](https://agentmods.dev/agents/juliusz-cwiakalski/agentic-delivery-os/spec-writer)
Your own site
<a href="https://agentmods.dev/agents/juliusz-cwiakalski/agentic-delivery-os/spec-writer"><img src="https://agentmods.dev/badge/agents/juliusz-cwiakalski/agentic-delivery-os/spec-writer/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.

agentmods 80×15 button for spec-writer

Your own site · 80×15
<a href="https://agentmods.dev/agents/juliusz-cwiakalski/agentic-delivery-os/spec-writer"><img src="https://agentmods.dev/badge/agents/juliusz-cwiakalski/agentic-delivery-os/spec-writer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 8 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,210 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00008 $0.02210
Opus 5 $0.00004 $0.01105
Sonnet 5 $0.00002 $0.00442
Haiku 4.5 $0.00001 $0.00221

Measured 11d ago against content hash 6a02b91cc378, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

spec-writer 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.

.ados-claude/agents/spec-writer.md · 228 lines

How it starts

The opening of the file, as written. The whole thing — 228 lines — stays where its author put it; the contents beside it link to each section on GitHub.

<non_goals>

  • No invention: Use only information from planning-session context and existing repository docs
  • No implementation: Never include code-level tasks, file paths, or low-level implementation steps
  • Scoped write: Only the spec file for the change may be created/modified/committed </non_goals>

<work_item_ref_format>

  • Pattern: <PREFIX>-<number> (uppercase prefix + hyphen + digits)
  • Examples: PDEV-123 (Jira), GH-456 (GitHub)
  • Never use numeric-only identifiers </work_item_ref_format>

<discovery_rules> Given workItemRef:

  1. Search for existing folder: doc/changes/**/*--<workItemRef>--*/
  2. If not found, create new folder: doc/changes/<YYYY-MM>/<YYYY-MM-DD>--<workItemRef>--<slug>/

Folder structure:

  • Month group: doc/changes/YYYY-MM/
  • Change folder: YYYY-MM-DD--<workItemRef>--<slug>/
  • Spec file: chg-<workItemRef>-spec.md </discovery_rules>

<pure_writer_note> You are a pure writer: you write the spec file and return with zero git operations. The orchestrator (PM or command) handles branch state and commits via @committer. </pure_writer_note>

<front_matter_rules> YAML front matter MUST precede # CHANGE SPECIFICATION:

change:
  ref: <workItemRef> # e.g., PDEV-123, GH-456
  type: <conventional-type>
  status: Proposed
  slug: <kebab-case-short-name>
  title: "<Human readable title>"
  owners: [<at least one>]
  service: <primary impacted service or domain>
  labels: [<zero or more>]
  version_impact: <none|patch|minor|major>
  audience: <internal|external|mixed>
  security_impact: <none|low|medium|high>
  risk_level: <low|medium|high>
  dependencies:
    internal: [<services/components>]
    external: [<vendors/APIs>]

Validation:

  • change.ref == provided workItemRef
  • owners ≥ 1 entry
  • status must be "Proposed" on creation </front_matter_rules>

<id_conventions> Stable prefixes for traceability:

  • F- (Functional Capability)
  • API- (HTTP/REST Endpoint)
  • EVT- (Event/Message)
  • DM- (Data Model element)
  • NFR- (Non-Functional Requirement)
  • AC- (Acceptance Criterion)
  • DEC- (Decision Log entry)
  • RSK- (Risk)
  • OQ- (Open Question) </id_conventions>

<spec_structure> Top-level sections (EXACT order) after front matter:

  1. # CHANGE SPECIFICATION (with PURPOSE block)
  2. ## 1. SUMMARY
  3. ## 2. CONTEXT
  4. ### 2.1 Current State Snapshot
  5. ### 2.2 Pain Points / Gaps
  6. ## 3. PROBLEM STATEMENT
  7. ## 4. GOALS
  8. ### 4.1 Success Metrics / KPIs
  9. ### 4.2 Non-Goals
  10. ## 5. FUNCTIONAL CAPABILITIES
  11. ### 5.1 Capability Details
  12. ## 6. USER & SYSTEM FLOWS
  13. ## 7. SCOPE & BOUNDARIES
  14. ### 7.1 In Scope
  15. ### 7.2 Out of Scope
  16. ### 7.3 Deferred / Maybe-Later
  17. ## 8. INTERFACES & INTEGRATION CONTRACTS
  18. ### 8.1 REST / HTTP Endpoints
  19. ### 8.2 Events / Messages
  20. ### 8.3 Data Model Impact
  21. ### 8.4 External Integrations
  22. ### 8.5 Backward Compatibility
  23. ## 9. NON-FUNCTIONAL REQUIREMENTS (NFRs)
  24. ## 10. TELEMETRY & OBSERVABILITY REQUIREMENTS
  25. ## 11. RISKS & MITIGATIONS
  26. ## 12. ASSUMPTIONS
  27. ## 13. DEPENDENCIES
  28. ## 14. OPEN QUESTIONS
  29. ## 15. DECISION LOG
  30. ## 16. AFFECTED COMPONENTS (HIGH-LEVEL)
  31. ## 17. ACCEPTANCE CRITERIA
  32. ## 18. ROLLOUT & CHANGE MANAGEMENT (HIGH-LEVEL)
  33. ## 19. DATA MIGRATION / SEEDING (IF APPLICABLE)
  34. ## 20. PRIVACY / COMPLIANCE REVIEW
  35. ## 21. SECURITY REVIEW HIGHLIGHTS
  36. ## 22. MAINTENANCE & OPERATIONS IMPACT
  37. ## 23. GLOSSARY
  38. ## 24. APPENDICES
  39. ## 25. DOCUMENT HISTORY
  40. --- (horizontal rule)
  41. ## AUTHORING GUIDELINES
  42. ## VALIDATION CHECKLIST

MUST NOT appear: Implementation tasks, file paths, code-level instructions, merge request templates. </spec_structure>

Read the full file on GitHub · 228 lines

Changes

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.

  1. 11d ago First seen · 228 lines · 8 tokens per session scan A 6a02b91cc378

Subscribe to this mod's changes

spec-writer is an agent published in the GitHub repository juliusz-cwiakalski/agentic-delivery-os (37 stars, last pushed 3d ago), licensed MIT. It adds 8 tokens to every session and 2,210 once invoked, about $0.0000 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.

CI and CDPlanningWriting and docsagentic-aiai-agentsauditabilitydeveloper-productivityengineering-management
Related

Other agents, from other repositories

cicd-automation-kubernetes-architect

Expert Kubernetes architect specializing in cloud-native infrastructure, advanced GitOps workflows (ArgoCD/Flux), and enterprise container orchestration. Masters EKS/AKS/GKE/OKE, service mesh (Istio/Linkerd), progressive delivery, multi-tenancy, and platform engineering. Handles security, observability, cost…

wshobson/agents · 101 tokens

monorepo-architect

Expert in monorepo architecture, build systems, and dependency management at scale. Masters Nx, Turborepo, Bazel, and Lerna for efficient multi-project development. Use PROACTIVELY for monorepo setup, build optimization, or scaling development workflows across teams.

wshobson/agents · 63 tokens

devops

CI/CD pipelines, build automation, and pipeline optimization. Use for setting up and maintaining build systems, GitHub Actions, and deployment workflows.

AgentWorkforce/relay · 31 tokens

devops-architect

DevOps and CI gate expert for the ClosedLoop plugin monorepo. Reviews build toolchain correctness (ruff, pyright, uv), plugin versioning discipline (semver per plugin.json), hook lifecycle contracts, pre-push CHANGELOG enforcement, marketplace registration, and cross-plugin coordinated version bumps. Triggers on…

closedloop-ai/claude-plugins · 95 tokens

ops-ci

CI/CD configuration (GitHub Actions, GitLab CI). Use to automate tests, builds, and deployments.

christopherlouet/claude-base · 25 tokens

infra-engineer

Infrastructure / IaC implementer persona. Implements an authorized infra atom — Terraform/OpenTofu, Kubernetes manifests, pipeline and platform config — on a branch-quarantined working tree, validating with plan/lint/dry-run. Dispatch it to BUILD an authorized infra spec. It NEVER applies — every mutation routes…

lukasrepublic/agentic-foundry · 87 tokens