spae-fix

spae-fix is a skill for Claude Code, Codex from mystilleef/spae-framework. It costs 32 tokens per session (1,876 once invoked), scanned C, original, MIT.

A controlled repair step in the SPAE workflow that addresses only the gaps listed in FIX.md for the active task. Test-driven changes are changes guided and checked by tests.

In plain words
What is it for?
It is for making minimal fixes, running the required tests, and returning the task to the checking phase.
Why use it?
It prevents unrelated edits and keeps repairs focused on the problems already identified by the checking phase.

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/mystilleef/spae-framework/spae-fix
Any agent
npx skills add mystilleef/spae-framework --skill spae-fix
Clone the repo
git clone --depth 1 https://github.com/mystilleef/spae-framework

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for spae-fix

README.md
[![agentmods](https://agentmods.dev/badge/skills/mystilleef/spae-framework/spae-fix.svg)](https://agentmods.dev/skills/mystilleef/spae-framework/spae-fix)
Your own site
<a href="https://agentmods.dev/skills/mystilleef/spae-framework/spae-fix"><img src="https://agentmods.dev/badge/skills/mystilleef/spae-framework/spae-fix.svg" alt="Measured on agentmods" height="20"></a>
Per session 32 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,876 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 1 finding. 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 $0.00032 $0.01876
Opus 5 $0.00016 $0.00938
Sonnet 5 $0.00006 $0.00375
Haiku 4.5 $0.00003 $0.00188

Measured 5d ago against content hash a119345e188e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade C, and why

spae-fix scanned grade C with 1 finding 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 5d 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.

Hidden instructionshighPrompt injection

Directives inside HTML comments, invisible characters or bidirectional overrides are read by the model and not by the person reviewing the file.

<!-- prettier-ignore-start -->
skills/spae-fix/SKILL.md · 188 lines

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.

Fix (SPAE)

When to use

  • STATE.json reports phase: fix.
  • FIX.md lists pre-classified gaps for the active in-progress task.

Goal

  • Close only the active task's named FIX.md gaps through minimal, test-driven changes.
  • Return the workstream to /check without task completion, cursor movement, plan edits, or scope expansion.

Input

Read:

  • STATE.json in .spae/current/ for task management (consult references/STATE.md for field reference, directives, and phase snapshots).
  • FIX.md in .spae/current/ for gaps to address.
  • Project source, tests, configuration, docs, and command output required by the named gaps.

Testing

See references/testing-guide.md for test structure, isolation, mocking, assertion, and performance standards.

Cleanup

See references/cleanup-guide.md for the self-introduced-artifact checklist and diff-only audit scope.

Workflow

  1. GATE—Read .spae/current/STATE.json; confirm phase: fix and an active task identifier. Self-heal state drift: if tasks[active_task_id] reads "todo", correct it to "in_progress" and write STATE.json before proceeding. Halt on state drift: if tasks[active_task_id] reads "done", halt. Read .spae/current/FIX.md; confirm its task identifier matches the active task and its ## Gaps list supplies concrete actionable gaps. Halt on missing, malformed, or mismatched input; report the failed precondition; make no changes.
  2. ORIENT—Goal: close the named gaps for one active task and return it to /check. Leave PLAN.md, SPEC.md, task completion, cursor movement, forward tasks, and unrelated project concerns untouched.
  3. PLAN—List each pre-classified FIX.md gap. Map its required test surface: expected behavior, failure modes, and edge cases. Use the task Intent only for context; never expand scope from it, Acceptance, Verification, forward tasks, seams, or observations.
  4. ACT—For each named gap:
    • Write a failing or gap-reproducing test covering expected behavior, failure modes, and edge cases.
    • Write the minimal source, test, configuration, or documentation change required by that gap.
    • Run targeted checks; repeat test→implement until the gap passes.

Read the full file on GitHub · 188 lines

Files

What ships with it

4 files 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.

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. 5d ago First seen · 188 lines · 32 tokens per session scan C a119345e188e

Subscribe to this mod's changes

spae-fix is a skill published in the GitHub repository mystilleef/spae-framework (1 stars, last pushed 1mo ago), licensed MIT. It adds 32 tokens to every session and 1,876 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it C with 1 finding (hidden instructions). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.