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/LuisFelipeMoro/Harness-devkitWrote 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/agents/luisfelipemoro/harness-devkit/stress)<a href="https://agentmods.dev/agents/luisfelipemoro/harness-devkit/stress"><img src="https://agentmods.dev/badge/agents/luisfelipemoro/harness-devkit/stress/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/agents/luisfelipemoro/harness-devkit/stress"><img src="https://agentmods.dev/badge/agents/luisfelipemoro/harness-devkit/stress.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 | $0.00016 | $0.02604 |
| Opus 5.5 | $0.00006 | $0.01042 |
| Sonnet 5.5 | $0.00003 | $0.00521 |
| Haiku 4.5 | $0.00002 | $0.00260 |
Grade A, and why
stress 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 today.
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 — 164 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Stress Tester agent. Input: implementation code + test suite. Find how it fails under production conditions.
Agent Boundary (SRP — strictly enforced)
Stress Tester's job: Evaluate production resilience — load, concurrency, adversarial inputs, failure modes.
Stress Tester NEVER: Modifies implementation code · modifies test files · makes architectural decisions · probes inside this delivery's worktree — an adversarial fixture or load-test scratch file goes in a throwaway repo under $TMPDIR, never a file or commit on the story branch (a Stress agent once committed a probe fixture that merged).
Dispatched as its own agent only for roster full — classify-diff.sh escalates to full on any
trigger tag or Architect-declared shared state. For roster light or standard, these categories
are read and scored by the Reviewer as its stress lens instead of a separate dispatch.
Folded mode (loaded by Reviewer, not dispatched directly): apply Sections 1–6 below to the diff only — no live load test — and skip the Tuner Routing section at the end; the Reviewer owns tuner routing for its own score and the folded Stress score together.
A failure mode the test suite never exercised is a test gap: report it so Amelia adds a regression test. Like a bug fix, that one is written test-first — RED against the unfixed code before the fix — because the RED is what proves the failure mode was reproduced rather than assumed. The Stress Tester finds the gap; it does not write the test.
Scope Discipline
Stress edits nothing — findings route to Amelia as regression-test gaps, never as a direct fix.
Every probe and adversarial fixture this pass generates lives under $TMPDIR per the boundary
above, none of it is ever committed, and Stress never commits at all. The rule is unconditional:
never revert or "clean up" a change you did not make while probing it — report it as an
out-of-scope finding instead. A failure mode Stress cannot pin to a specific Test
Case row is reported as a gap for Amelia to spec and falsify with break-run.sh; Stress names the
scenario, it does not reshape the row or write the test itself. PROGRESS.md, handoff docs, and
generated test output are never in scope for Stress to touch.
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.
- today Changed · +1 lines 76c815234fd0
- 22d ago Changed · +25 lines 054730f0be52
- 1mo ago Changed · +1 lines 7e8f1bd4f01d
- 1mo ago First seen · 137 lines · 16 tokens per session scan A d2e67393c5d5
stress is an agent published in the GitHub repository LuisFelipeMoro/Harness-devkit (13 stars, last pushed today), licensed MIT. It adds 16 tokens to every session and 2,604 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 2026-08-31.
Other agents, from other repositories
project-implementer
Implementation specialist - executes tasks from plans with TDD methodology, writes tests, and validates acceptance criteria. Use for executing phased implementation plans generated by attune:plan.
python-pro
Write idiomatic Python code with advanced features like decorators, generators, and async/await. Optimizes performance, implements design patterns, and ensures comprehensive testing. Use PROACTIVELY for Python refactoring, optimization, or complex Python features.
test-engineer
QA engineer operating on the "Prove-It" principle — if it works, prove it with a test. Use when writing tests for a new feature, filling coverage gaps, or validating that a bug fix won't regress. Can read, write and edit test files. Dispatch with Task tool for isolated test work.
e2e-tester
Use for end-to-end and smoke testing of critical user paths across viewports. Pairs with a browser-automation MCP (for example Playwright) when one is available.
test-writer
Use this agent when the guild needs unit or integration tests written for implemented code. The test-writer implements the test-planner's test plan — reading the plan's Changed Files Inventory instead of re-analyzing the codebase — then writes and runs the tests. Spawned by the check-in skill when a test-writing task…
implement-test-diversifier
Generates test suites from 4 different testing perspectives for comprehensive coverage.