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/deep-researchnpx skills add 5uck1ess/devkit --skill deep-researchgit 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 | $0.00223 | $0.00501 |
| Opus 5 | $0.00112 | $0.00251 |
| Sonnet 5 | $0.00045 | $0.00100 |
| Haiku 4.5 | $0.00022 | $0.00050 |
Grade A, and why
deep-research 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.
What it actually says
Deep Research
ACH-enhanced deterministic research: clarify → perspectives → decompose → parallel search → extract claims → hypotheses → disconfirm → evidence matrix (with sensitivity check) → self-critique → synthesize.
Costs more tokens (~400k budget) but produces higher-confidence results by actively trying to disprove answers.
Invoke
Start the workflow via the devkit engine:
Use the devkit_start tool with workflow: "deep-research" and input: "{input}".
Then follow each step the engine returns. Call devkit_advance after completing each step. The engine controls step order, gates, and loops. Do NOT skip steps.
Rules
- Perspectives first — ground queries in real viewpoints, not LLM brainstorming
- Disconfirm > confirm — try to KILL hypotheses, not prove them
- Summarize immediately — never carry raw fetched content forward
- Evidence matrix is mandatory — no skipping the structured comparison
- Sensitivity check is mandatory — know how fragile your conclusion is
- Self-critique before output — catch your own biases
- Cite everything — every claim links to its source
- Confidence calibration — HIGH/MEDIUM/LOW based on evidence robustness, not gut feel
- Be honest about uncertainty — "I don't know" with good reasoning beats a confident wrong answer
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 · 31 lines · 223 tokens per session scan A f9ded86b7c66
deep-research is a skill published in the GitHub repository 5uck1ess/devkit (5 stars, last pushed 13d ago), licensed MIT. It adds 223 tokens to every session and 501 once invoked, about $0.0011 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.
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/).