Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/ChipAlexandru/strategy-consultantnpx agentmods add commands/chipalexandru/strategy-consultant/researchWrote 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/chipalexandru/strategy-consultant/research)<a href="https://agentmods.dev/commands/chipalexandru/strategy-consultant/research"><img src="https://agentmods.dev/badge/commands/chipalexandru/strategy-consultant/research.svg" alt="Measured on agentmods" 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 | $0.00023 | $0.00540 |
| Opus 5 | $0.00012 | $0.00270 |
| Sonnet 5 | $0.00005 | $0.00108 |
| Haiku 4.5 | $0.00002 | $0.00054 |
Grade A, and why
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 8d 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 — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CONTINUATION COMMAND — do not use as a fresh entry point
This command continues an existing engagement. Before any other tool call:
- Check for an engagement workspace (
./engagements/<slug>-<date>/engagement-state.json, or — for legacy engagements —./engagement/precision-anchor.md). - If a workspace exists → continue from the research phase using its state.
- If a workspace does NOT exist → STOP. Invoke /engagement instead. engagement-manager will route to the correct starting phase, including this one if appropriate.
Do not attempt to run this phase cold. Upstream artifacts (Precision Anchor, Client Question Checklist, Source Material Extraction Log, data-source answers, engagement-state.json) are produced by earlier phases and required inputs here. Reconstructing them inside this command is not the fix — routing through engagement-manager is.
/research — Parallel Research with Validation (continuation)
If you see unfamiliar placeholders or need to check which tools are connected, see CONNECTORS.md.
Important: This plugin assists with strategic analysis and research but does not constitute professional consulting, financial, or legal advice. All outputs should be reviewed by qualified professionals before use in decision-making.
Resume the research phase of an active engagement. Deploys two independent research agents in parallel, then a validator, against the upstream artifacts produced by problem-definition.
Usage
/research <research question or topic>
The <topic> argument is informational only — the authoritative question comes from the active engagement's Precision Anchor, not from the argument string.
If no engagement workspace exists, do not attempt to start one. Stop and route the user to /engagement.
Workflow
This command resumes the research skill inside an active engagement. The skill's preflight gate verifies the upstream artifacts (precision-anchor.md, client-question-checklist.md, source-material-extraction-log.md, step0-answers.md, engagement-state.json) are present and that problem-definition is in completed_phases. If any required item is missing, the skill stops and routes back to engagement-manager.
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.
- 8d ago First seen · 49 lines · 23 tokens per session scan A f8162a0e0ec7
research is a command published in the GitHub repository ChipAlexandru/strategy-consultant (4 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 23 tokens to every session and 540 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 2026-08-31.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.