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.
npx skills add joris887/exosuit --skill manual-testgit clone --depth 1 https://github.com/joris887/exosuitWrote 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/skills/joris887/exosuit/manual-test)<a href="https://agentmods.dev/skills/joris887/exosuit/manual-test"><img src="https://agentmods.dev/badge/skills/joris887/exosuit/manual-test.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 | $0.01146 |
| Opus 5 | $0.00012 | $0.00573 |
| Sonnet 5 | $0.00005 | $0.00229 |
| Haiku 4.5 | $0.00002 | $0.00115 |
Grade A, and why
manual-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 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 — 151 lines — stays where its author put it; the contents beside it link to each section on GitHub.
manual-test
Preparing manual test session...
1. Gather Context
Read these files to understand what to test:
Recent Changes
# What changed recently (last 20 commits or since last tag)
git log --oneline -20
git diff --stat HEAD~10
Identify which areas of the project were modified and map to testable features.
Known Issues
Check the backlog for known gaps and bugs that are still TODO:
- Read relevant epic files in
docs/reference/backlog/ - These are confirmed issues — test around them but don't spend time re-discovering them
Recent Sprint Work
- Read
docs/progress.mdfor latest sprint info - Check
docs/sprints/for recent sprint specs with acceptance criteria
UAT Coverage
- Read
docs/testing/UAT_COVERAGE.md(if it exists) for test case status - Identify which areas have not been tested yet
Product Requirements & Personas
- Read
docs/context/personas.md(if it exists) for lean persona cards — these provide CONTEXT, GOALS, FRUSTRATIONS, BEHAVIORS, EVALUATES BY, and FAILURE LOOKS LIKE fields that directly inform exploratory testing in Phase 3C - Read
docs/reference/PRD_SUMMARY.md(if it exists) for success criteria and user flows - Section 3 (success criteria) identify what to prioritize testing
- Section 4 (user flows) provide the core scenarios to regression test
- If both personas.md and PRD Section 2 exist, prefer personas.md (richer behavioral detail for test generation)
2. Pre-Flight Checks
Before manual testing, verify the system is ready:
Run the project's test command (from CLAUDE.md) to ensure automated tests pass.
If pre-flight fails, fix issues before proceeding to manual testing.
3. Generate Test Plan
Generate a structured test plan covering three areas:
A. Regression Tests (from recent changes)
Based on the git diff, generate specific test scenarios for recently modified code:
#### Regression: [Area changed]
- [ ] **Scenario**: [What to test] — **Steps**: [How to test] — **Expected**: [What should happen]
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 151 lines · 23 tokens per session scan A de5f6d763308
manual-test is a skill published in the GitHub repository joris887/exosuit (4 stars, last pushed 18d ago), licensed MIT. It adds 23 tokens to every session and 1,146 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 skills, from other repositories
plan-pipeline-execute
Execute a validated plan: worktree isolation, TDD scaffolding, level-based parallel agents, quality gate with smoke test, PR creation and merge. Handles everything through to merged PR.
qa
Systematic QA testing of a web application: diff-aware, tiered, with fix-and-verify loop.
plan-pipeline-eng-review
Engineering architecture gate: lock architecture, diagrams, edge cases, and test matrix before writing implementation code.
ci-all
Full CI pipeline: run local tests, type check, push branch, and return the pipeline URL. The only command you need before opening a PR.
generate-tests
Generate comprehensive tests for specified code.
ci-tests
Run the test suite for the current repo, auto-detecting Python (pytest/uv), Node (vitest/pnpm), or Rust (cargo test).