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.
git clone --depth 1 https://github.com/SienkLogic/plan-build-runWrote 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/commands/sienklogic/plan-build-run/research-phase)<a href="https://agentmods.dev/commands/sienklogic/plan-build-run/research-phase"><img src="https://agentmods.dev/badge/commands/sienklogic/plan-build-run/research-phase/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/commands/sienklogic/plan-build-run/research-phase"><img src="https://agentmods.dev/badge/commands/sienklogic/plan-build-run/research-phase.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 | $0.00020 | $0.00403 |
| Opus 5.5 | $0.00008 | $0.00161 |
| Sonnet 5.5 | $0.00004 | $0.00081 |
| Haiku 4.5 | $0.00002 | $0.00040 |
Grade A, and why
research-phase scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Note: This is a standalone research command. For most workflows, use /pbr:plan-phase which integrates research automatically.
Use this command when:
- You want to research without planning yet
- You want to re-research after planning is complete
- You need to investigate before deciding if a phase is feasible
@.planning/ROADMAP.md @.planning/STATE.md
PHASE_INFO=$(pbr-tools roadmap get-phase "$ARGUMENTS")
Error if phase not found. Extract phase_number, phase_name, goal.
2. Check Existing Research
Look for .planning/phases/{NN}-*/RESEARCH.md.
If exists, offer: 1) Update research, 2) View existing, 3) Skip.
3. Gather Context
Read phase description, requirements, and prior decisions.
4. Spawn Researcher
Task({
subagent_type: "pbr:researcher",
prompt: "Research implementation approach for Phase {N}: {name}\n\nPhase goal: {goal}\nRequirements: {requirements}\nPrior decisions: {decisions}\n\nWrite to: .planning/phases/{NN}-{slug}/{NN}-RESEARCH.md"
})
5. Handle Return
## RESEARCH COMPLETE: Display summary, offer/pbr:plan-phase {N}## RESEARCH INCONCLUSIVE: Show what was attempted, offer options
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 · 60 lines · 20 tokens per session scan A bdfa5945d35f
research-phase is a command published in the GitHub repository SienkLogic/plan-build-run (19 stars, last pushed 6mo ago), licensed MIT. It adds 20 tokens to every session and 403 once invoked, about $0.0001 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 2026-09-03.
Other commands, from other repositories
sync
Check guide/landing synchronization status.
diff-docs
Compare official Anthropic docs baseline vs current snapshot (no network — instant).
refresh-docs
Re-fetch official Anthropic Claude Code docs and update current snapshot (baseline unchanged).
planning
Planning semanal de equipo con revisión de RFCs, priorización, asignación por responsable/pareja/squad y seguimiento.
auditar-seguridad
Auditoría de seguridad estática del código (OWASP Top 10, SecDevOps).
data-policy
Documentar qué datos toca el framework, qué sale a APIs externas y generar política de privacidad. Usa cuando el usuario dice "data policy", "política de datos", "privacy policy", "datos sensibles", "GDPR", "data handling", "APIs externas", "external APIs", "qué datos se comparten". Mapea data flows y genera política…