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/oborchers/fractional-ctoWrote 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/oborchers/fractional-cto/stress-test)<a href="https://agentmods.dev/commands/oborchers/fractional-cto/stress-test"><img src="https://agentmods.dev/badge/commands/oborchers/fractional-cto/stress-test/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/oborchers/fractional-cto/stress-test"><img src="https://agentmods.dev/badge/commands/oborchers/fractional-cto/stress-test.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 | $0.00014 | $0.01229 |
| Opus 5.5 | $0.00006 | $0.00492 |
| Sonnet 5.5 | $0.00003 | $0.00246 |
| Haiku 4.5 | $0.00001 | $0.00123 |
Grade A, and why
stress-test 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 5d 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 — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Stress-test a planning document using the red-team/blue-team adversarial review pattern from the stress-test plugin.
Follow this process:
Step 1: Plan File
If no plan file was provided as an argument, use AskUserQuestion to ask the user which file to stress-test:
- Ask them to provide the path to their plan document
Read the plan file to confirm it exists and understand its contents. Identify the plan's type (implementation plan, business plan, design plan, etc.) and the surrounding context (codebase, supporting documents, config files).
Step 2: Context Assessment
Briefly assess the surrounding context available for grounding:
- Is there a codebase the plan references?
- Are there supporting documents, configs, or data files?
- What systems or APIs does the plan depend on?
Present this assessment to the user so they understand what the agents will work with.
Step 3: Stressor Mode
Use AskUserQuestion to ask the user which stressor mode the red team should use:
- Grounded -- What-if questions strictly tied to plan artifacts and code. Every question references a specific file, config, dependency, or code path. Best for detailed implementation plans with rich surrounding context.
- Creative -- Adds extreme, cross-domain stressors inspired by Residuality Theory. Includes business, regulatory, team, market, and "what survives?" questions that go beyond what the artifacts suggest. Best for plans where hidden coupling and blind spots matter more than line-by-line coverage.
- Both -- Runs grounded questions first, then a separate creative pass. Most thorough but produces more questions.
Step 4: Tool Scope
Use AskUserQuestion to ask the user what tool scope the blue team should have:
- Local artifacts only -- Read, Grep, Glob. The blue team can only reference the plan and local files. Fastest and safest. Best when surrounding context is rich (e.g., a full codebase).
- + Web research -- Adds WebSearch and WebFetch. The blue team can look up external documentation, API specs, standards, and benchmarks. Good when the plan references external systems or standards.
- + System verification -- Adds Bash and MCP tools. The blue team can query live APIs, check configurations, run diagnostic commands. Most powerful but requires the systems to be accessible.
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.
- 5d ago First seen · 108 lines · 14 tokens per session scan A 20e68ed724b3
stress-test is a command published in the GitHub repository oborchers/fractional-cto (32 stars, last pushed 5d ago), licensed MIT. It adds 14 tokens to every session and 1,229 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 2026-10-13.
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.
speckit.bug.fix
Apply the remediation from a bug assessment and record what was changed.