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/dont-reinventnpx skills add 5uck1ess/devkit --skill dont-reinventgit 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 | $0.00637 |
| Opus 5 | $0.00015 | $0.00318 |
| Sonnet 5 | $0.00006 | $0.00127 |
| Haiku 4.5 | $0.00003 | $0.00064 |
Grade A, and why
dont-reinvent 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 3d 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 — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Don't Reinvent the Wheel
Before writing any non-trivial utility, helper, or tool — check if it already exists.
The Search Order
- Language stdlib / builtins —
path.join(),os.path,filepath.Join()exist. Don't write your own. - Framework built-ins — most frameworks have solutions for routing, validation, auth, caching. Use them.
- Established packages — if there's a well-maintained package with meaningful adoption and recent commits, prefer it over custom code.
- Existing tools / plugins / MCP servers — before building a new CLI wrapper or integration, check if one exists. Run a quick search.
- Internal codebase — search the project for existing utilities before creating new ones. Someone may have already solved this.
Only build custom when none of the above genuinely fit.
Why This Matters
Every custom solution is code you maintain forever:
- Bug fixes are your problem
- Edge cases are your problem
- Updates when dependencies change are your problem
- Documentation is your problem
A well-maintained library handles all of this for you. The 20 minutes you "save" by writing it yourself costs hours in future maintenance.
When Custom Is Justified
- The existing solutions don't fit and adapting them is harder than building
- The existing solutions are unmaintained (no commits in 12+ months, unresolved security issues)
- The scope is truly trivial (a 3-line helper doesn't need a dependency)
- Performance requirements rule out general-purpose solutions (measure first, don't assume)
- Security requirements demand full control over the implementation
Red Flags You're Reinventing
- Writing a date parser, URL parser, retry wrapper, or logger from scratch
- Building a custom HTTP client wrapper around fetch/axios
- Writing string manipulation utilities that exist in lodash/underscore/stdlib
- Creating a custom config file format instead of using JSON/YAML/TOML
- Building a task queue when BullMQ/Celery/existing solutions exist
- Writing a custom test framework instead of using the ecosystem standard
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.
- 3d ago First seen · 60 lines · 30 tokens per session scan A 7cc8968a2d0f
dont-reinvent is a skill published in the GitHub repository 5uck1ess/devkit (5 stars, last pushed 14d ago), licensed MIT. It adds 30 tokens to every session and 637 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.
agent-teams
Experimental Agent Teams orchestration — run CCGodMode agents as parallel teammates with SharedTaskList coordination (requires CLAUDECODEEXPERIMENTALAGENTTEAMS=1).
cost-efficiency
Smart Routing — the DEFAULT CCGodMode routing policy. Risk-based, minimal-agent paths that preserve required safety gates for the changed scope.
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/).