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/5uck1ess/devkit/adrnpx skills add 5uck1ess/devkit --skill adrgit clone --depth 1 https://github.com/5uck1ess/devkitWhat 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 | $0.00030 | $0.00478 |
| Opus 5 | $0.00015 | $0.00239 |
| Sonnet 5 | $0.00006 | $0.00096 |
| Haiku 4.5 | $0.00003 | $0.00048 |
Grade A, and why
adr 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 yesterday.
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.
What it actually says
ADR — Architecture Decision Record
Capture the why behind architectural decisions so future-you (and future-agents) don't reverse them without context.
Step 1: Gather Context
Identify:
- What decision was made (or needs to be made)
- What alternatives were considered
- What constraints drove the choice
- What the consequences are
If the user hasn't specified, ask one question: "What decision are you documenting?"
Step 2: Check Existing ADRs
mkdir -p .devkit/docs/adr
ls .devkit/docs/adr/ 2>/dev/null | grep -oE '^[0-9]+' | sort -n | tail -1
Add 1 to the highest number found, zero-padded to 4 digits. If no output, the directory is empty — start at 0001.
Step 3: Write the ADR
Create .devkit/docs/adr/NNNN-short-title.md:
# NNNN. Short Decision Title
**Date:** YYYY-MM-DD
**Status:** accepted | proposed | deprecated | superseded by [NNNN]
## Context
What is the issue? What forces are at play? 2-4 sentences max.
## Decision
What did we decide? State it directly. 1-3 sentences.
## Alternatives Considered
- **Alternative A** — why rejected (1 line)
- **Alternative B** — why rejected (1 line)
## Consequences
What follows from this decision? Both positive and negative. Bullet list.
Rules
- Keep it short. An ADR is a reference, not an essay. Under 200 words total.
- One decision per ADR. If there are two decisions, write two ADRs.
- Use plain language. No jargon that requires context to parse.
- Status is usually
accepted. Useproposedonly if the user hasn't decided yet. - Never modify the substantive content of existing ADRs (Context, Decision, Alternatives, Consequences). When superseding, only update the old ADR's Status line to
superseded by [MMMM].
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.
- yesterday First seen · 64 lines · 30 tokens per session scan A b3590b4d6360
adr is a skill published in the GitHub repository 5uck1ess/devkit (5 stars, last pushed 13d ago), licensed MIT. It adds 30 tokens to every session and 478 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 2026-08-31.
Other skills, from other repositories
dynamic-workflows
Ultracode / Max-Parallel mode — dynamic workflows fan work out across tens–hundreds of adversarially-verified parallel subagents for large, decomposable jobs (codebase-wide audits, big migrations, cross-checked research). Opt-in; higher token spend.
cost-efficiency
Smart Routing — the DEFAULT CCGodMode routing policy. Risk-based, minimal-agent paths that preserve required safety gates for the changed scope.
agent-teams
Experimental Agent Teams orchestration — run CCGodMode agents as parallel teammates with SharedTaskList coordination (requires CLAUDECODEEXPERIMENTALAGENTTEAMS=1).
quality-gates
Parallel quality gate orchestration — @validator and @tester run simultaneously after @builder, with mandatory decision matrix for pass/fail routing.
sprint-planning
Plan-first orchestration (ADR-004): comprehensive PLAN.md, sprint files with write-scope ownership, preflight checks, serialized integration, and the release sprint. Use for any non-trivial or multi-part request BEFORE dispatching agents.
workflows
CCGodMode Full-Gates workflow definitions — used for high-risk work and when Smart Routing escalates. Default routing is Smart Routing (skills/cost-efficiency/).