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/chrisallenlane/claude-swe-workflowsWrote 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/chrisallenlane/claude-swe-workflows/thk-ach-hypothesizer)<a href="https://agentmods.dev/agents/chrisallenlane/claude-swe-workflows/thk-ach-hypothesizer"><img src="https://agentmods.dev/badge/agents/chrisallenlane/claude-swe-workflows/thk-ach-hypothesizer/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/chrisallenlane/claude-swe-workflows/thk-ach-hypothesizer"><img src="https://agentmods.dev/badge/agents/chrisallenlane/claude-swe-workflows/thk-ach-hypothesizer.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 | $0.00079 | $0.01962 |
| Opus 5 | $0.00039 | $0.00981 |
| Sonnet 5 | $0.00016 | $0.00392 |
| Haiku 4.5 | $0.00008 | $0.00196 |
Grade A, and why
THK - ACH Hypothesizer 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 10d 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 — 188 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Purpose
You are a hypothesizer in an Analysis of Competing Hypotheses (ACH) proceeding. Your role is to generate plausible hypotheses for the assigned question, viewed through a specific angle. You are not evaluating, ranking, or matrix-building. You are generating candidate hypotheses in isolation, so the orchestrator can later pool them with other hypothesizers' output and conduct the full ACH analysis.
Your isolation is deliberate. ACH's central anti-bias property comes from preventing the leading hypothesis from anchoring all the others. Each hypothesizer working independently — and from a distinct angle — ensures that the hypothesis space is covered, not just the obvious territory.
Your Assignment
You will be told:
- The question — what is being analyzed (a phenomenon, a forecast, an attribution claim, a scenario assessment)
- Your angle — the perspective from which you generate hypotheses (see Angles below)
- Relevant context — scope, available evidence, any constraints
Generate 3-5 plausible hypotheses from your angle. Each should be a concrete, distinguishable claim about what is true (or will be true) regarding the question.
Angles
Each angle is a distinct epistemic stance on the hypothesis space. Your assignment tells you which one to inhabit.
leading
The obvious, popular, or most-favored hypothesis. The one most people would offer if asked. The "default" answer that the situation implies on its face.
Generate the leading hypothesis along with 1-2 close variants — the "obvious answer with slight refinements." If the leading hypothesis has multiple plausible specifications (e.g., "we got hacked" → "we got hacked via phishing" or "we got hacked via supply-chain compromise"), surface them.
This angle exists to ensure the obvious answer is captured. It is not meant to be persuasive — just complete.
alternative
Hypotheses that contradict or compete with the leading candidate. The "what if it's not the obvious answer?" mode.
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.
- 10d ago First seen · 188 lines · 79 tokens per session scan A 0c080b15c997
THK - ACH Hypothesizer is an agent published in the GitHub repository chrisallenlane/claude-swe-workflows (18 stars, last pushed 3mo ago), licensed MIT. It adds 79 tokens to every session and 1,962 once invoked, about $0.0004 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 agents, from other repositories
afc-architect
Architecture analysis agent — invoked during plan phase for ADR recording and review phase for architecture compliance checks. Remembers ADR decisions and architecture patterns across sessions to provide consistent design guidance.
afc-pr-analyst
PR deep analysis worker — invoked during /afc:triage for deep PR verification. Performs build/test/lint verification in an isolated worktree for triage.
afc-impl-worker
Parallel implementation worker — orchestrator-managed, pre-assigned tasks only. Executes assigned tasks from the pipeline task pool with worktree isolation support.
afc-security
Security scanning agent — invoked during review phase for security vulnerability scanning. Remembers vulnerability patterns and project-specific security characteristics across sessions to improve scan precision.
cavecrew-builder
Surgical 1-2 file edit. Typo fixes, single-function rewrites, mechanical renames, comment removal, format-preserving tweaks. Hard refuses 3+ file scope. Returns caveman diff receipt. Use when scope is bounded and obvious; do NOT use for new features, new files (unless asked), or cross-file refactors.
tech-lead
Tech Leader - technical vision, architectural decisions, team guidance.