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 commands/agricidaniel/ace-claude-code/research-phasegit clone --depth 1 https://github.com/AgriciDaniel/ace-claude-codeWhat 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 | $0.00010 | $0.01017 |
| Opus 5 | $0.00005 | $0.00508 |
| Sonnet 5 | $0.00002 | $0.00203 |
| Haiku 4.5 | $0.00001 | $0.00102 |
Grade A, and why
ace:research-phase 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 — 213 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Use when the phase involves:
- Unfamiliar technologies
- Complex integrations
- Industry best practices needed
- Multiple competing solutions to evaluate
Required: @.ace/planning/STATE.md @.ace/planning/PROJECT.md @.ace/planning/ROADMAP.md
Optional: @.ace/planning/codebase/STACK.md (for tech context)
1. Identify Research Topics
Read phase goal and identify:
- Technologies mentioned
- Integration patterns needed
- Unknown areas requiring research
+==============================================================+
| RESEARCH PHASE [N] |
+==============================================================+
Phase: [N] - [Phase Name]
Goal: [Phase goal]
Identified Research Topics:
1. [Topic 1] - [Why it needs research]
2. [Topic 2] - [Why it needs research]
3. [Topic 3] - [Why it needs research]
+==============================================================+
2. Confirm Research Scope
Use AskUserQuestion: "I've identified these topics for research. Any to add or remove?"
- Options: "Proceed with these" / "Add topics" / "Remove some"
3. Spawn Research Agents
Launch parallel Explore agents for each topic:
CRITICAL: Send ALL Task calls in ONE message.
For Each Topic:
Research [Topic] for Phase [N] of [Project Name].
Context:
- Project type: [From config.json]
- Stack: [From STACK.md or PROJECT.md]
- Goal: [Phase goal]
Research:
1. Best practices and patterns
2. Common pitfalls to avoid
3. Recommended libraries/tools
4. Example implementations
Return structured findings.
4. Collect Research Results
Wait for all agents to complete.
Aggregate findings into sections:
- Technologies evaluated
- Recommended approaches
- Risks and mitigations
- Code examples found
5. Create Research Document
Write to .ace/references/phase-[N]-research.md:
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 · 213 lines · 10 tokens per session scan A 1503e9f2069c
ace:research-phase is a command published in the GitHub repository AgriciDaniel/ace-claude-code (24 stars, last pushed 4mo ago), licensed MIT. It adds 10 tokens to every session and 1,017 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 commands, from other repositories
canvas
AI-orchestrated visual canvas production — create, populate, layout, present, generate, and export Obsidian canvases.
document
Generate documentation for code.
test
Generate comprehensive tests for a file or function.
review
Review code for best practices and issues.
fix-issue
Analyze and fix a GitHub issue.
migrate
Create migration plan for upgrade.