spell-tester

A separate agent that tests a draft reusable AI workflow against realistic scenarios. It reports whether the draft passes, needs refinement, or solves a different problem than described.

In plain words
What is it for?
Use it during workflow creation to test content, workflow, discipline, or subagent spells.
Why use it?
It exposes missing instructions or a mismatch between a workflow's purpose and its behavior before you use it.

Agent

Install

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.

agentmods
npx agentmods add agents/redhuntlabs/wizard/spell-tester
Clone the repo
git clone --depth 1 https://github.com/redhuntlabs/wizard
Per session 41 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,484 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00041 $0.01484
Opus 5 $0.00020 $0.00742
Sonnet 5 $0.00008 $0.00297
Haiku 4.5 $0.00004 $0.00148

Measured 2d ago against content hash 0b10b98c2504, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

spell-tester 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 2d 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.

agents/spell-tester.md · 160 lines

How it starts

The opening of the file, as written. The whole thing — 160 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Spell Tester

You have been dispatched as a subagent to test a draft spell. Your job is to attempt the draft on realistic scenarios and return one of three verdicts:

  • PASS — the draft works as written, no changes needed
  • NEEDS-REFINEMENT — the draft has specific gaps; list them
  • SCOPE-CHANGED — the draft attempts to solve a different problem than its description claims

Mode selection

Read the kind field of the draft spell's frontmatter.

  • kind: disciplineDISCIPLINE MODE
  • kind: content, workflow, or subagentSTANDARD MODE

Inputs you receive

The parent agent dispatches you with this context (and only this context):

  1. The full text of the draft SKILL.md file
  2. The user's stated goal (one or two sentences)
  3. The user's domain (e.g., "academic research", "marketing", "law")
  4. Up to 2 examples of past inputs the user has handled in this domain

You receive NO other context. You are stateless.

STANDARD MODE (content / workflow / subagent)

Step 1: Propose 2 or 3 example scenarios

Read the draft's description, When to use, and What you bring (Inputs). Generate 2 or 3 scenarios that match those triggers and inputs. They should be:

  • Realistic for the user's domain. No invented edge cases unless the draft claims to handle edge cases.
  • Distinct. Don't test the same shape twice.
  • Concrete. Specific names, numbers, dates — not "a meeting" but "a 30-minute hiring sync with three engineers."

Step 2: Execute the draft on each scenario

Follow the How it works (Steps) section literally. Do not adapt, summarize, or skip steps. If a step is ambiguous, that is a finding — note it and try a reasonable interpretation.

For each scenario, produce the output the draft promises in What you get (Output).

Step 3: Score against the Quality bar

Compare each output against the draft's Quality bar criteria. For each criterion, mark met, partially met, or not met.

Step 4: Return verdict

Read the full file on GitHub · 160 lines

Changes

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.

  1. 2d ago First seen · 160 lines · 41 tokens per session scan A 0b10b98c2504

Subscribe to this mod's changes

spell-tester is an agent published in the GitHub repository redhuntlabs/wizard (9 stars, last pushed 4mo ago), licensed MIT. It adds 41 tokens to every session and 1,484 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.

Related

Other agents, from other repositories

pr-reviewer

Reads the git diff after a feature is pushed, tags every finding as Blocker or Nit, and produces ONE rollup task containing all findings. Does NOT read CI, does NOT merge. Use after the SWE has pushed the feature branch and before the orchestrator hands the PR back to the human for squash-merge.

iusztinpaul/squid · 68 tokens

software-engineer

Implements a single groomed task assigned by the orchestrator. Writes code and tests locally. Does NOT commit until the Tester has reviewed and approved. Use when a task is groomed and ready for implementation, or when the Tester has returned feedback that needs to be addressed.

iusztinpaul/squid · 59 tokens

oncall-engineer

Monitors CI/CD after git push. If the pipeline fails, identifies the related task from commit messages, reopens it, diagnoses the root cause, and hands a concrete fix task to the SWE — then re-verifies the pipeline turns green once the fix lands. Owns pipeline health; does not change application code itself. Use after…

iusztinpaul/squid · 85 tokens

_index

Festival is files and two CLIs the agent loop actually touches: fest and camp, installed and kept current by a third tool, festival. It works with any agent that can run shell commands and read files, which is nearly all of them. There is no plugin to install for the core loop: the agent runs fest next, reads the task…

Obedience-Corp/festival · 0 tokens

codex

Codex runs Festival through a plugin that carries the skills and a session-start hook. The loop is the same fest next loop it is everywhere else. The plugin's job is narrow: make sure the fest and camp CLIs exist, and make sure the agent knows the vocabulary.

Obedience-Corp/festival · 0 tokens

gemini

Gemini CLI installs Festival as an extension straight from GitHub, in one command. The extension carries a context file that imports every Festival skill, and a session-start hook that installs the fest and camp CLIs.

Obedience-Corp/festival · 0 tokens