Borrowing it
Nothing to install: this file belongs to netdata/ai-viewer. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/netdata/ai-viewer/master/.agents/skills/project-workflow/SKILL.mdgit clone --depth 1 https://github.com/netdata/ai-viewerWrote 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.
[](https://agentmods.dev/skills/netdata/ai-viewer/project-workflow)<a href="https://agentmods.dev/skills/netdata/ai-viewer/project-workflow"><img src="https://agentmods.dev/badge/skills/netdata/ai-viewer/project-workflow/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.
<a href="https://agentmods.dev/skills/netdata/ai-viewer/project-workflow"><img src="https://agentmods.dev/badge/skills/netdata/ai-viewer/project-workflow.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00072 | $0.03991 |
| Opus 5.5 | $0.00029 | $0.01596 |
| Sonnet 5.5 | $0.00014 | $0.00798 |
| Haiku 4.5 | $0.00007 | $0.00399 |
Grade A, and why
project-workflow 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 1mo 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 — 329 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Workflow
Purpose
This skill is the assistant's runtime checklist. The contract lives in AGENTS.md (the "Three Reviewer Gates" section is the operating model); the durable spec lives in .agents/sow/specs/workflow.md; this file is the operational pattern the assistant follows every time. Load it at the start of every meaningful task. If the assistant ever notices it has started writing code without consulting this skill, stop and restart from the top.
Roles
| Role | Model | Job |
|---|---|---|
| CTO (master assistant) | me | Research, decide, update specs, write tests, implement code, run gates, verify, commit, and report. |
| Helper subagents | optional | Bounded read-only investigation or summarization when it saves context/time. They are not the default implementation path. |
| External reviewers | glm, minimax, kimi, mimo, deepseek, qwen |
Milestone quality gates for gap analysis, implementation plan, and implementation on meaningful chunks. They do not design or implement the work. |
The CTO owns the work. External reviewers are acceptance gates, not the normal
work engine. Do not run reviewers during ordinary exploration or before the CTO
has personally completed the current stage artifact. Before any external
reviewer invocation, load .agents/skills/project-second-opinions/SKILL.md,
complete its reviewer-readiness checklist, and record the evidence in the SOW or
work ledger.
Non-negotiable review rule: every review is open-ended over the whole milestone/gate scope. After a real P0/P1/P2 reviewer finding, verify the cited class and count all occurrences during claim verification, then perform a fresh open-ended review of the entire milestone from scratch before any rerun. A class-only review is biased and turns reviewers into discovery scouts.
The Cycle (Invariant Order)
1. Re-orient → read SOWs, specs, skills
2. Gap → analyze what must be true for the goal to be satisfied
3. Gap Review → reviewers vote NOTHING MORE CAN BE DONE
4. Plan → write the implementation plan
5. Plan Review → reviewers vote READY FOR IMPLEMENTATION
6. Spec → update or create specs FIRST
7. Test → write failing tests against the new spec
8. Code → CTO implements directly; make tests pass
9. Gates → run every automated quality gate locally
10. Impl Review → reviewers vote PRODUCTION GRADE
11. Discipline → run the Discipline Checklist
12. Commit → one commit per logical step; spec + tests + code + docs together
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.
- 1mo ago First seen · 329 lines · 72 tokens per session scan A 1bd33323712e
project-workflow is a skill published in the GitHub repository netdata/ai-viewer (2 stars, last pushed 1mo ago), licensed MIT. It adds 72 tokens to every session and 3,991 once invoked, about $0.0003 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.
Other skills, from other repositories
compiler-commit
Use when you want to verify compiler changes and commit with the correct convention. Runs tests, lint, and format, then commits with the [compiler] or [rust-compiler] prefix.
vhs-e2e-gif
Record a test run, a TUI session, or any terminal command as a GIF with VHS and attach it to a GitHub PR as a release-hosted asset, never a repo commit. Use when asked to record an e2e run, demo a fix on a PR, attach a GIF or screen recording to a pull request, show a test passing visually, or produce a terminal…
langsmith-observability
LLM observability platform for tracing, evaluation, and monitoring. Use when debugging LLM applications, evaluating model outputs against datasets, monitoring production systems, or building systematic testing pipelines for AI applications.
release-safety
Release safety rules. INVOKE WHEN: yarn release, npm publish, release canary, release packages, publishing, skip checks, skip tests. NEVER skip checks or tests without explicit permission.
walkeros-understanding-development
Use when contributing to walkerOS, before writing code, or when unsure about project conventions. Covers build/test/lint workflow, XP principles, folder structure, and package usage.
migrate-state-management
Migrate Redux or React Context to the correct state option (React Query for server state, nuqs for URL/shareable state, Zustand for global client state). Use when refactoring away from Redux/Context, moving state to the right store, or when the user asks to migrate state management.