adr-commit

adr-commit is a skill for Claude Code, Codex from Eilodon/DPS-Superskills-MCP. It costs 50 tokens per session (3,471 once invoked), scanned A, original, Apache-2.0.

A branch-completion procedure that requires a short Architecture Decision Record, a written explanation of an important technical choice, before integration.

In plain words
What is it for?
Checking tests, identifying the branch state, choosing the base branch, and preparing a merge, pull request, or branch closeout.
Why use it?
It prevents a finished branch from being merged or closed without recording key decisions and reviewing tracked pattern debt, meaning known design problems.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is python3 tools/dps.py sync.

Good fit Checking tests, identifying the branch state, choosing the base branch, and preparing a merge, pull request, or branch closeout.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/Eilodon/DPS-Superskills-MCP
agentmods
npx agentmods add skills/eilodon/dps-superskills-mcp/adr-commit

Made for: Claude Code, Codex.

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 adr-commit

README.md
[![agentmods](https://agentmods.dev/badge/skills/eilodon/dps-superskills-mcp/adr-commit/github.svg)](https://agentmods.dev/skills/eilodon/dps-superskills-mcp/adr-commit)
Your own site
<a href="https://agentmods.dev/skills/eilodon/dps-superskills-mcp/adr-commit"><img src="https://agentmods.dev/badge/skills/eilodon/dps-superskills-mcp/adr-commit/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 adr-commit

Your own site · 80×15
<a href="https://agentmods.dev/skills/eilodon/dps-superskills-mcp/adr-commit"><img src="https://agentmods.dev/badge/skills/eilodon/dps-superskills-mcp/adr-commit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 50 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,471 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 $0.00050 $0.03471
Opus 5.5 $0.00020 $0.01388
Sonnet 5.5 $0.00010 $0.00694
Haiku 4.5 $0.00005 $0.00347

Measured 2mo ago against content hash a8c3990ccd44, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

adr-commit 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 2mo 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.

docs/DPS-superskills-v5.2.1/adr-commit/SKILL.md · 414 lines

How it starts

The opening of the file, as written. The whole thing — 414 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ADR-Commit — Finish a Branch with a Decision Record

Completes a development branch with a mandatory ADR gate and PATTERN-DEBT lifecycle review.

Announce: "I'm using adr-commit to complete this work."


Step 1: Verify Tests

npm test / cargo test / pytest / go test ./...

Failing tests → stop. Show failures. Do not proceed.


Step 2: Detect Environment

GIT_DIR=$(cd "$(git rev-parse --git-dir)" 2>/dev/null && pwd -P)
GIT_COMMON=$(cd "$(git rev-parse --git-common-dir)" 2>/dev/null && pwd -P)
State Menu Cleanup
GIT_DIR == GIT_COMMON 4 options None
GIT_DIR != GIT_COMMON, named branch 4 options Provenance-based
GIT_DIR != GIT_COMMON, detached HEAD 3 options None

Step 3: Determine Base Branch

git merge-base HEAD main 2>/dev/null || git merge-base HEAD master 2>/dev/null

Step 3.5: ADR Gate ← MANDATORY

Cannot proceed to Step 4 without a committed ADR.

# Recent commits for context (auto-injected):
!git log --oneline -10 2>/dev/null

Choose output target:

# DPS present? → append to .dps/spec/ADR.md
# DPS absent?  → standalone file (legacy format, unchanged)
ls .dps/spec/ADR.md 2>/dev/null && echo "DPS mode" || echo "Standalone mode"

DPS ADR format (khi DPS present):

---
## ADR-{{N}}: {{Feature Name}}

<!-- dps:id=ADR-{{N}} -->
<!-- dps:type=adr -->

**DATE:** {{YYYY-MM-DD}}
**STATUS:** ACCEPTED
**CHANGE CLASSIFICATION:** {{DESIGN CHANGE | SPEC BUG | IMPLEMENTATION BUG | INTENT DRIFT | EXTERNAL CONSTRAINT CHANGE}}

### Context
{{What problem forced this decision?}}

### Decision
{{What was built or changed? One concrete paragraph.}}

### Alternatives Considered
{{At least one alternative and why rejected.}}

### Consequences
{{What improved? What worsened? What debt was created?}}

### CONFIDENCE: {{HIGH | MEDIUM | LOW}}
### VOLATILITY: {{STABLE | WATCHFUL | VOLATILE}}
### VALIDATION TARGET: {{Required if CONFIDENCE = LOW}}
### WATCH SIGNAL: {{Required if VOLATILITY = WATCHFUL or VOLATILE}}
### LAST CONFIRMED: {{YYYY-MM-DD}} (INITIAL)

### IMPACT RADIUS
Components: {{list component names from DPS Component Registry}}
Schemas: {{list schema names from DPS CONTRACTS.md}}
Cascade Review: {{✅ Not needed | 🔄 Pending: component/schema list}}

### Evidence (T1/T2)
{{Ran command → output | CI passed | peer confirmed}}

### Part 10: Cycle Retrospective
{{For knowledge-compound: what surprised us, what to do differently}}
---

Read the full file on GitHub · 414 lines

Files

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.

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. 2mo ago First seen · 414 lines · 50 tokens per session scan A a8c3990ccd44

Subscribe to this mod's changes

adr-commit is a skill published in the GitHub repository Eilodon/DPS-Superskills-MCP (0 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 50 tokens to every session and 3,471 once invoked, about $0.0002 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 2026-08-31.