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/drynpx skills add 5uck1ess/devkit --skill drygit 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 | $0.00020 | $0.00454 |
| Opus 5 | $0.00010 | $0.00227 |
| Sonnet 5 | $0.00004 | $0.00091 |
| Haiku 4.5 | $0.00002 | $0.00045 |
Grade A, and why
dry 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
DRY (Don't Repeat Yourself)
The Rule of Three
Don't abstract on the first duplication. Wait for three instances.
- First time — Just write it.
- Second time — Notice the duplication, wince, keep going.
- Third time — Now extract. You have enough examples to see the real pattern.
Premature abstraction is worse than duplication. Wrong abstractions are expensive to undo.
When Duplication Is Fine
Not all duplication is bad. Duplication is acceptable when:
- The duplicated code serves different concerns. Test setup that looks similar to production code isn't "duplication" — they change for different reasons.
- The cost of coupling exceeds the cost of duplication. If extracting a shared function means two unrelated modules now depend on each other, keep them separate.
- The "duplication" is coincidental. Two things look the same today but will evolve independently. Forcing them to share code creates a false coupling.
The test: if one copy changes, must the other change too? If yes, extract. If maybe not, leave it.
Extracting the Right Abstraction
When you do extract, get the abstraction right:
- Name it for what it does, not where it came from.
formatCurrencynotextractedFromOrderPage. - Parameterize the differences. The parts that vary between call sites become parameters.
- Don't over-parameterize. If the shared function needs 8 config options to handle all cases, the cases are probably too different to share.
- Keep it simple. If the abstraction is harder to understand than the duplication, the duplication was better.
The Real DRY Principle
DRY is about knowledge, not code. The principle says every piece of knowledge should have a single authoritative source. Two functions with identical code but representing different business rules are not a DRY violation.
"Every piece of knowledge must have a single, unambiguous, authoritative representation within a system." — Andy Hunt & Dave Thomas
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 · 42 lines · 20 tokens per session scan A 61bb2b321fb5
dry is a skill published in the GitHub repository 5uck1ess/devkit (5 stars, last pushed 13d ago), licensed MIT. It adds 20 tokens to every session and 454 once invoked, about $0.0001 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/).