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/o2alexanderfedin/strategic-research-automation-templateWrote 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/o2alexanderfedin/strategic-research-automation-template/execute-task)<a href="https://agentmods.dev/commands/o2alexanderfedin/strategic-research-automation-template/execute-task"><img src="https://agentmods.dev/badge/commands/o2alexanderfedin/strategic-research-automation-template/execute-task/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/o2alexanderfedin/strategic-research-automation-template/execute-task"><img src="https://agentmods.dev/badge/commands/o2alexanderfedin/strategic-research-automation-template/execute-task.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 | $0.00011 | $0.00690 |
| Opus 5 | $0.00005 | $0.00345 |
| Sonnet 5 | $0.00002 | $0.00138 |
| Haiku 4.5 | $0.00001 | $0.00069 |
Grade A, and why
execute-task 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 9d 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 — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Execute Single Task
You are executing the /execute-task command to run one task within a sprint.
Purpose
Execute a single research task by invoking the appropriate specialized skill (technical-researcher, market-analyst, solution-architect, compliance-analyst, roadmap-planner, or report-synthesizer) with full context.
Steps to Execute
Step 1: Validate Arguments
Check $1 (sprint-number) is 2-digit format 01-99 Check $2 (task-number) is 01-06 Verify prerequisites:
- Sprint $1 exists in config/sprint-config.yml
- Task file exists: sprints/$1-/0$2-.md
- Context files populated
Step 2: Load Configuration and Context
Read config/project-config.yml for execution parameters Read config/sprint-config.yml for sprint details Read context files (client-info.md, company-profile.md) Read task definition file: sprints/$1-/0$2-.md
Step 3: Determine Appropriate Skill
Map task number to skill:
- Task 01 → technical-researcher (or research-synthesizer with technical focus)
- Task 02 → market-analyst (or research-synthesizer with market focus)
- Task 03 → solution-architect (or research-synthesizer with architecture focus)
- Task 04 → compliance-analyst (or research-synthesizer with compliance focus)
- Task 05 → roadmap-planner (or research-synthesizer with roadmap focus)
- Task 06 → report-synthesizer
Step 4: Invoke Skill via Task Tool
Use Task tool to invoke appropriate skill with context:
- Sprint number: $1
- Task number: $2
- Configuration paths
- Context file contents
- Output directory: temp/$1-/0$2-/
Skill will autonomously:
- Research according to task questions
- Create 5-7 research files
- Generate synthesis document
- Cite all claims with authoritative sources
Step 5: Monitor Execution
Track skill progress Update progress tracking tool if monitoring task list Handle any errors gracefully
Step 6: Validate Task Output
Verify:
- temp/$1-/0$2-/ directory exists
- Minimum 5 research files created
- synthesis.md file exists
- Files are substantive (>500 words each)
- Citations present
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.
- 9d ago First seen · 98 lines · 0 tokens per session scan A 678fa716b36a
execute-task is a command published in the GitHub repository o2alexanderfedin/strategic-research-automation-template (19 stars, last pushed 9mo ago), licensed MIT. It adds 11 tokens to every session and 690 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
prp-prd
Interactive PRD generator - problem-first, hypothesis-driven product spec with back-and-forth questioning.
jira
Retrieve a Jira ticket, analyze requirements, update status, or add comments. Uses the jira-integration skill and MCP or REST API.
setup-pm
Configure your preferred package manager (npm/pnpm/yarn/bun).
checkpoint
Create or verify a checkpoint in your workflow.
projects
List known projects and their instinct statistics.
update-counts
Update all hardcoded counts (skills, agents, marketplace repos/skills) across documentation from filesystem.