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/shinpr/codex-workflows/task-analyzernpx skills add shinpr/codex-workflows --skill task-analyzergit clone --depth 1 https://github.com/shinpr/codex-workflowsWhat 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 | $0.00023 | $0.00887 |
| Opus 5 | $0.00012 | $0.00443 |
| Sonnet 5 | $0.00005 | $0.00177 |
| Haiku 4.5 | $0.00002 | $0.00089 |
Grade A, and why
task-analyzer 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 — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Task Analyzer
Use references/skills-index.yaml as the available workflow-skill catalog.
Task Analysis Process
1. Understand Task Essence
Identify the fundamental purpose beyond the surface request.
- What problem or outcome is the user actually asking to resolve?
- What observable result marks completion?
- Which superficial response could miss that result?
Return the essence as a concise purpose, not a restatement of the requested operation.
2. Identify Task Type
Classify the immediate work as implementation, fix, refactoring, design, documentation, quality/review, diagnosis, research, or continuation. Preserve an explicitly invoked recipe or supplied governing artifact as the entry point.
3. Match Skills by Task Evidence
Extract task tags and match them to skills-index.yaml. Consider implicit relationships that materially change execution:
| Task evidence | Consider |
|---|---|
| Observed failure or error handling | ai-development-guide, testing |
| Code implementation or refactoring | coding-rules, testing |
| Design or implementation planning | documentation-criteria, implementation-approach |
| Real boundary proof | integration-e2e-testing |
| Agent handoff or multi-agent workflow | llm-friendly-context, subagents-orchestration-guide |
Select skills in this priority order:
- Essential — changes the primary action.
- Quality — changes proof or failure handling.
- Process — governs the explicitly selected workflow.
- Supplementary — resolves a concrete remaining risk.
Select the smallest set whose rules change execution or verification. A recipe's Required Skills already define its set.
4. Generate Metacognitive Guidance
Generate only questions and warnings that can change the current approach. Cover, when applicable:
- the task's essential quality criterion;
- evidence needed before the first change;
- a likely superficial or local-only failure;
- a dependency, boundary, or verification risk;
- the smallest useful first action and its rationale.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 103 lines · 23 tokens per session scan A b216ad86c6e1
task-analyzer is a skill published in the GitHub repository shinpr/codex-workflows (38 stars, last pushed 4d ago), licensed MIT. It adds 23 tokens to every session and 887 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 2026-08-30.
Other skills, from other repositories
chrome-cdp
Drive a headless Chrome over the Chrome DevTools Protocol (CDP) for browser QA — navigate, click, fill forms, read the DOM/accessibility tree, screenshot, and assert. Use whenever a task requires loading a web page and interacting with it like a user. Chrome is launched by a bash step (recipe below); this skill…
metrics-instrumentation
Specification for instrumenting an opik-backend workflow with operational OpenTelemetry metrics — per-stage throughput/latency/error counters and native histograms, dimensioned per-customer (workspace). Use when a pipeline (scoring, ingestion, experiments, jobs) needs per-stage visibility. Covers metric emission only…
new-app
Scaffold a new Atomic Agents project from scratch — create the directory, pyproject.toml, env file, first agent, and a runnable entry point. Use when the user asks to start a new atomic-agents project from scratch, says "scaffold" / "new project" / "start from zero", or runs /atomic-agents:new-app.
ax-go-flow
Use when writing Go code with github.com/ax-llm/ax/packages/go for flows, nodes, program graphs, nested programs, dynamic options, caching, and optimizer components.
ax-python-agent
Use when writing Python code with axllm for agents, child delegation, tools, MCP, citations, persistent playbook learning, stage instructions, runtime state, final typed responses, and direct-respond executor skipping.
chat-complex-documents
Chat with and search your complex documents — ask questions, extract tables and fields, and get answers grounded in the source. Connects the hosted Unstructured Transform MCP server to parse, structure, and enrich PDFs, Word/Excel/PowerPoint, images, scanned files, emails, and 60+ other formats into clean, AI-ready…