confirm-red-failure

A skill for checking that a test fails because the required source code is missing or outdated. This is the red step in test-driven development, where tests guide implementation by failing first.

In plain words
What is it for?
It is for validating new or changed tests before coding and reporting defective tests or contradictory requirements.
Why use it?
It prevents developers from fixing tests or mistaking setup errors for real implementation work.

Skill for Claude CodeCodex

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 skills/nullhack/temple8/confirm-red-failure
Any agent
npx skills add nullhack/temple8 --skill confirm-red-failure
Clone the repo
git clone --depth 1 https://github.com/nullhack/temple8

Made for: Claude Code, Codex.

Per session 30 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 328 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 $0.00030 $0.00328
Opus 5 $0.00015 $0.00164
Sonnet 5 $0.00006 $0.00066
Haiku 4.5 $0.00003 $0.00033

Measured 2d ago against content hash 04a0b2dace4e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

confirm-red-failure 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.

.opencode/skills/confirm-red-failure/SKILL.md · 14 lines

What it actually says

Confirm Red Failure

  1. Load [[software-craft/tdd]] — red/green discipline and the right-reason rule.
  2. Remove the pending marker from all the target contract's tests for this cycle. Removing the decorator may orphan import pytest when the test used it for nothing else — run ruff and drop the unused import; that is a lint side-effect of un-marking, not a behaviour edit. Do not author tests; they already exist with full bodies.
  3. Run the tests. Confirm the failure is ours: IF the source .py is absent and the deferred in-body import raises ImportError THEN new work; IF the source .py exists but is stale against the changed contract and an assertion fails THEN rework. Either is the right reason per [[software-craft/tdd]].
  4. IF the red fails for the wrong reason (a typo, a bad fixture, a contract the tests themselves violate) THEN reject it — do not patch the test.
  5. IF investigation reveals the contract itself is the problem — a referenced cassette is missing, an assertion no correct implementation could satisfy, the spec contradicts itself — THEN append the finding to .cache/<session_id>/journal.md (contract, the gap, the evidence) and fire reveals-gap. This routes back to plan, not green.
  6. Read the target contract's .pyi first, not the whole tree.
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 · 14 lines · 30 tokens per session scan A 04a0b2dace4e

Subscribe to this mod's changes

confirm-red-failure is a skill published in the GitHub repository nullhack/temple8 (11 stars, last pushed 28d ago), licensed MIT. It adds 30 tokens to every session and 328 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 2026-08-30.