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 agentmods add skills/gxfn/wakeflow/regression-designnpx skills add GxFn/Wakeflow --skill regression-designgit clone --depth 1 https://github.com/GxFn/WakeflowWrote 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/gxfn/wakeflow/regression-design)<a href="https://agentmods.dev/skills/gxfn/wakeflow/regression-design"><img src="https://agentmods.dev/badge/skills/gxfn/wakeflow/regression-design.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 | $0.00037 | $0.00735 |
| Opus 5 | $0.00018 | $0.00367 |
| Sonnet 5 | $0.00007 | $0.00147 |
| Haiku 4.5 | $0.00004 | $0.00073 |
Grade A, and why
regression-design 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 4d 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 — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Regression Design
Turn a behavior or bug into durable regression coverage guidance. This skill designs tests and evidence; it does not implement product fixes unless a test card explicitly authorizes Test to do so.
Source Skills Used
mattpocock/skills/engineering/tdd: public interfaces, behavior over implementation, vertical red-green cycles, no horizontal test dumps, and no refactor while red.diagnose: correct regression seam comes after a real feedback loop and reproduction.- Industry basis: test pyramid and behavior-focused testing.
Wakeflow Role
Use this skill when:
- a bug has been reproduced and needs a regression plan;
- a requirement needs behavior-first coverage before implementation;
- a target result claims coverage and Test must judge whether the seam is right;
- a controller wants to know what evidence would prevent recurrence.
Core Principle
Test observable behavior through a public seam. A good regression survives internal refactors. A bad regression tests private methods, mocks internal collaborators unnecessarily, or verifies implementation shape instead of user or system behavior.
Workflow
- Name the behavior.
- What capability must remain true?
- Which actor or integration observes it?
- Choose the public seam.
- API endpoint, CLI command, UI flow, public function, daemon job, integration boundary, or documented output.
- Prefer the highest seam that proves the behavior.
- Check the bug pattern.
- Does the seam exercise the real call chain?
- Does it cover the failure as observed?
- If not, state that the architecture lacks a correct seam.
- Specify fail-before/pass-after evidence.
- Expected failing signal before fix or before intended behavior exists.
- Expected passing signal after implementation.
- Design one tracer bullet first.
- One behavior.
- One test or observation.
- Minimal fixture.
- Clear assertion.
- Add further behaviors incrementally.
- Do not write all tests first.
- Each new test should reflect learning from the previous cycle.
- Return guidance to the controller or owning product window.
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.
- 4d ago First seen · 109 lines · 37 tokens per session scan A 3b8100320e99
regression-design is a skill published in the GitHub repository GxFn/Wakeflow (5 stars, last pushed 11d ago), licensed MIT. It adds 37 tokens to every session and 735 once invoked, about $0.0002 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
archon
Autonomous multi-session campaign agent. Decomposes large work into phases, delegates to sub-agents, reviews output, and maintains campaign state across context windows. Use for work that spans multiple sessions and needs persistent state, quality judgment, and strategic decomposition.
fleet
Parallel campaign orchestrator. Runs multiple campaigns in coordinated waves within a single session. Spawns 2-3 agents per wave in isolated worktrees, collects discoveries, shares context between waves. Use when work decomposes into 3+ independent streams that can run simultaneously.
daemon
Continuous autonomous operation mode. Keeps campaigns running 24/7 by chaining Claude Code sessions via RemoteTrigger. Each session picks up from the campaign's continuation state, works until context runs low or the phase completes, then schedules the next session. Auto-stops on campaign completion or budget…
evolve
Research-driven multi-cycle improvement director. Forms causal hypotheses about why scores are low, validates them with scout agents before attacking, dispatches axis-parallel fleet attacks, extracts transferable patterns, and runs indefinitely within a budget envelope. Accumulates a persistent belief model and…
improve
Autonomous quality improvement loop. Scores a target against a rubric, selects the highest-leverage axis, attacks it, verifies, documents, and loops. No pre-planning between iterations — each loop re-scores from scratch.
setup
First-run experience for the harness. Three modes: Recommended (guided, 3 min), Full Tour (guided + skill walkthrough, 8 min), and Express (zero questions, 30 sec). Installs hooks first, detects stack, configures harness.json, runs a live demo on real code, and prints a reference card.