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 agentmods add skills/elliot35/deterministic-agent-control-protocol/dev-standardsnpx skills add elliot35/deterministic-agent-control-protocol --skill dev-standardsgit clone --depth 1 https://github.com/elliot35/deterministic-agent-control-protocolWhat 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 | $0.00056 | $0.03211 |
| Opus 5 | $0.00028 | $0.01605 |
| Sonnet 5 | $0.00011 | $0.00642 |
| Haiku 4.5 | $0.00006 | $0.00321 |
Grade A, and why
dev-standards 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 2d 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 — 298 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Development Standards
This skill defines the mandatory workflows, quality gates, and coding standards for all changes to the deterministic-agent-control-protocol project.
Change Type Classification
Before starting work, classify the change:
| Type | Unit Tests | README Update | Architecture Diagrams | Release Notes | PR Required |
|---|---|---|---|---|---|
| New Feature | Required (must pass) | Yes | If related | Yes | No |
| Bug Fix | Required (cover the bug) | No | No | Yes | No |
| Re-architecture | Required (all affected) | Yes (full update) | Yes (mandatory) | Yes (full detail) | Yes (mandatory) |
| New Integration | Follow integration pattern | Yes (root + dedicated) | If related | Yes | No |
| New Policy | N/A | Yes (built-in policies section) | No | Yes | No |
Workflow Checklists
New Feature
Task Progress:
- [ ] 1. Create/update source files in src/
- [ ] 2. Add unit tests in tests/ mirroring src/ structure
(e.g., src/engine/foo.ts -> tests/engine/foo.test.ts)
- [ ] 3. Run `npm test` -- ALL tests must pass
- [ ] 4. Run `npm run lint` -- no type errors
- [ ] 5. Update README.md (feature description, usage, new CLI commands/API methods)
- [ ] 6. Update Mermaid diagrams in README.md if architecture or data flow changed
- [ ] 7. Add entry to RELEASE_NOTES.md under current unreleased version
- [ ] 8. Run impact check on examples/ and integrations/
- [ ] 9. Generate commit message
Bug Fix
Task Progress:
- [ ] 1. Write a FAILING unit test that reproduces the bug
- [ ] 2. Fix the bug in source code
- [ ] 3. Run `npm test` -- confirm the new test passes with all existing tests
- [ ] 4. Run `npm run lint` -- no type errors
- [ ] 5. Add entry to RELEASE_NOTES.md (Fixed section)
- [ ] 6. NO README update needed (unless bug was in documented behavior)
- [ ] 7. Run impact check on examples/ and integrations/
- [ ] 8. Generate commit message
Re-architecture
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.
- 2d ago First seen · 298 lines · 56 tokens per session scan A 95d1703c74e0
dev-standards is a skill published in the GitHub repository elliot35/deterministic-agent-control-protocol (88 stars, last pushed 6mo ago), licensed MIT. It adds 56 tokens to every session and 3,211 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 2026-08-30.
Other skills, from other repositories
harness
End-to-end workflow orchestrator. Walks the 11-phase pipeline, invoking each phase skill in order inside an internal loop, yielding at consent gates (/approve-direction, /approve-swarm, /grant-commit), and exiting cleanly on yield/failure/done. Decides swarm-vs-solo at Phase 6. Auto-loops /tdd on integrate failures…
claude-automation-recommender
Analyze a codebase and recommend Claude Code automations (hooks, subagents, skills, plugins, MCP servers). Use when user asks for automation recommendations, wants to optimize their Claude Code setup, mentions improving Claude Code workflows, asks how to first set up Claude Code for a project, or wants to know what…
code-structure
MANDATORY skill for ALL code generation. Enforces top-down composition, consistent abstraction layers, and proper module hierarchy. Apply every time you write or modify code — in any language — no exceptions.
memory-sync
Review the auto-extracted candidates in .claude/memory/pending.md and commit keepers to the canonical memory files (landmarks.md, libraries.md, decisions.md, landmines.md, conventions.md, pending-questions.md, backlog.md). Invoke at session start when the SessionStart hook reports pending candidates, or any time…
chore
Workflow track for tasks that need no TDD — documentation edits, governance count bumps, vendored-skill content updates, configuration tweaks, formatting, typo fixes, dependency bumps where no project code changes. Skips /scenario and /implement (no failing test to drive) and runs the work directly. archive…
code-browser
The primary tool for code-navigation questions in ANY language (frontend or backend) — walk the structural graph from an entry point (page, route, handler, command, main) down through imports to the IO boundary (network call, query, file read). Use this skill, in preference to the Explore agent or global grep…