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/claude-code-workflows/task-analyzernpx skills add shinpr/claude-code-workflows --skill task-analyzergit clone --depth 1 https://github.com/shinpr/claude-code-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 | $0.00026 | $0.00666 |
| Opus 5 | $0.00013 | $0.00333 |
| Sonnet 5 | $0.00005 | $0.00133 |
| Haiku 4.5 | $0.00003 | $0.00067 |
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 — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Task Analyzer
Use skills-index.yaml as the available skill catalog. Documentation routing and workflow Structural Scale belong to documentation-criteria, not this skill.
Process
1. Identify Task Essence
State the observable purpose beyond the surface operation. Preserve an explicitly invoked recipe or governing artifact as the entry point.
2. Match Skills to Task Evidence
Extract task-evidence tags and match them to the catalog. Add a skill only when its rules change the requested action, verification, or handling of a concrete risk.
| Task evidence | Consider |
|---|---|
| Observed defect or failure | ai-development-guide, testing-principles |
| Code implementation or refactoring | coding-principles, testing-principles |
| Requested design artifact | documentation-criteria |
| Multiple credible implementation strategies requiring cost comparison | implementation-approach |
| Observable cross-boundary behavior that cannot be proven more cheaply | integration-e2e-testing |
| React or TypeScript frontend code | typescript-rules and applicable frontend testing rules |
Select in this order:
governing: defines the requested output or selected workflow.risk-control: changes proof or handling of an activated failure mode.supplementary: resolves a concrete remaining risk.
3. Generate Execution Guidance
Generate only warnings and questions that can change skill selection, verification, escalation, or the first action. Prefer the smallest evidence-gathering action that can establish the target or cause.
Task analysis does not own Structural Scale, file-count estimation, documentation requirements, approval gates, implementation phases, or subagent topology.
Output
taskAnalysis:
essence: <fundamental purpose>
extractedTags: [<task evidence tag>]
selectedRules:
- skill: <skill name from skills-index.yaml>
priority: <governing|risk-control|supplementary>
reason: <how it changes execution or verification>
sections: [<relevant section name>]
metaCognitiveGuidance:
taskEssence: <fundamental purpose>
pastFailures: [<applicable known failure pattern>]
potentialPitfalls: [<task-specific risk>]
firstStep:
action: <smallest evidence-gathering or execution action>
rationale: <why it comes first>
metaCognitiveQuestions: [<question that can change the approach>]
warningPatterns:
- pattern: <applicable warning>
mitigation: <proportionate response>
What ships with it
1 file 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 · 74 lines · 26 tokens per session scan A e791d3c72742
task-analyzer is a skill published in the GitHub repository shinpr/claude-code-workflows (675 stars, last pushed 4d ago), licensed MIT. It adds 26 tokens to every session and 666 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
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/).