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/darkroomengineering/cc-settings/zero-tech-debtnpx skills add darkroomengineering/cc-settings --skill zero-tech-debtgit clone --depth 1 https://github.com/darkroomengineering/cc-settingsWhat 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 | $0.00061 | $0.00550 |
| Opus 5 | $0.00030 | $0.00275 |
| Sonnet 5 | $0.00012 | $0.00110 |
| Haiku 4.5 | $0.00006 | $0.00055 |
Grade A, and why
zero-tech-debt 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 — 35 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Zero Tech Debt
Rework the change from the intended end-state, not from the historical path that produced the current patch. The principles (no compat hacks, no abstractions you don't need, no dead branches) are in AGENTS.md — this skill is the workflow for applying them to a specific patch.
When to invoke
- A feature has accreted mode props, route aliases, or fallbacks across iterations
- A migration left behind a compatibility shim that no current caller uses
- You catch yourself preserving an old shape "just in case" with no concrete caller in mind
- The diff is bigger than the change it represents because it's making the old structure better instead of removing it
For restructuring code outside the current diff use /refactor. This skill is for the patch in front of you. (Claude Code 2.1.147 renamed /simplify to /code-review and removed the old cleanup-and-fix behavior; the native command is now a correctness reporter, not a code tightener.)
Steps
- State the intended end-state. One or two sentences. If you can't name it, stop and ask the user — you'll otherwise optimize toward the current shape.
- Search for real callers before preserving compatibility. For each mode prop, route alias, fallback branch, or wrapper: grep for current callers. No caller → delete it, don't improve it.
- Reshape around the final product surface. Prefer one clear component or flow over mode flags. Split only when there's an obvious boundary — state, layout, controls, or domain commands.
- Move shared rules to one place. Feature flags, permissions, route gating, URL state, and command naming should not be duplicated across pages or hidden inside view components.
- Verify the intended flow. Test the new behavior and any deleted assumptions that affect navigation, permissions, or persisted state.
Rules
- Optimize for the code that should exist, not the smallest diff from the old shape.
- Delete dead compatibility paths instead of making them better.
- Don't invent a generic framework for one feature.
- Keep the rework scoped to what makes the final shape coherent — don't drag in unrelated cleanup.
- Prefer names that describe product intent over implementation history (
AdminDashboardoverLegacyDashboardV2).
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 · 35 lines · 61 tokens per session scan A 4a766be48fd5
zero-tech-debt is a skill published in the GitHub repository darkroomengineering/cc-settings (42 stars, last pushed 4d ago), licensed MIT. It adds 61 tokens to every session and 550 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
dotfiles-bootstrap
Bootstrap a workstation with the dotfiles framework. Takes a GitHub user / owner+repo / explicit clone URL and runs dot init (which shells out to chezmoi) with the right safety prompts. Honors the active agent profile (ask / plan / apply / audit) so it defaults to dry-run in safer modes and full apply in apply.
astro-dso-doc
Generates a complete, polished HTML documentation page, a processing checklist, an AstroBin post JSON, a PixInsight process icon set (XPSM), AND a ready-to-paste PixInsight project Description field for a deep-sky object (DSO) astrophotography project. Use this skill whenever the user mentions astrophotography, a DSO…
document-code
Apply Google Style documentation standards to Python, Go, TypeScript, and Terraform code. Use when writing or reviewing code that needs docstrings/comments/JSDoc, when asked to "document this code", "add docstrings", "follow Google Style", or when improving code documentation quality. Supports Python docstrings, Go…
work-on-ticket
Fetches Jira ticket details, creates an appropriately named branch, and initiates the task planning workflow. Use when the user says "work on [TICKETID]" or similar phrases.
datadog
Use this skill when you need to search Datadog logs, query metrics, tail logs in real-time, trace distributed requests, investigate errors, compare time periods, find log patterns, check service health, or export observability data.
document-project
Generate comprehensive, professional project documentation structures including README, ARCHITECTURE, USERGUIDE, DEVELOPERGUIDE, and CONTRIBUTING files. Use when the user requests project documentation creation, asks to "document a project", needs standard documentation files, or wants to set up docs for a new…