fix-it-now

fix-it-now is a skill for Claude Code from mikestangdevs/craft-skills. It costs 157 tokens per session (1,243 once invoked), scanned A, original, MIT.

A coding workflow that treats a confirmed bug as work to fix during the current task, instead of merely recording it.

In plain words
What is it for?
Use it when you find a confirmed bug while auditing, reviewing, testing, or building another feature. It also addresses unfinished features with known gaps when they are part of the current work.
Why use it?
It prevents known defects from being forgotten after an audit, review, or unrelated coding task. Fixing while the cause and reproduction are fresh can avoid a later debugging session.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the craft-skills plugin — 17 skills shipped together

Good fit Use it when you find a confirmed bug while auditing, reviewing, testing, or building another feature. It also addresses unfinished features with known gaps when they are part of the current work.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/mikestangdevs/craft-skills/fix-it-now
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.

Any agent
npx skills add mikestangdevs/craft-skills --skill fix-it-now
Clone the repo
git clone --depth 1 https://github.com/mikestangdevs/craft-skills

Made for: Claude Code.

Or install craft-skills, the plugin that ships this one along with the rest of its 17 skills.

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 fix-it-now

README.md
[![agentmods](https://agentmods.dev/badge/skills/mikestangdevs/craft-skills/fix-it-now/github.svg)](https://agentmods.dev/skills/mikestangdevs/craft-skills/fix-it-now)
Your own site
<a href="https://agentmods.dev/skills/mikestangdevs/craft-skills/fix-it-now"><img src="https://agentmods.dev/badge/skills/mikestangdevs/craft-skills/fix-it-now/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.

agentmods 80×15 button for fix-it-now

Your own site · 80×15
<a href="https://agentmods.dev/skills/mikestangdevs/craft-skills/fix-it-now"><img src="https://agentmods.dev/badge/skills/mikestangdevs/craft-skills/fix-it-now.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 157 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,243 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00157 $0.01243
Opus 5 $0.00078 $0.00622
Sonnet 5 $0.00031 $0.00249
Haiku 4.5 $0.00016 $0.00124

Measured 9d ago against content hash 8f9b5b93bb9e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

fix-it-now 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 9d 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.

skills/rigor/fix-it-now/SKILL.md · 71 lines

How it starts

The opening of the file, as written. The whole thing — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Fix It Now

The failure mode this fixes

An audit runs, finds six real defects, and produces a beautiful document listing them. The document gets filed. The defects stay. Three weeks later one of them detonates in front of a customer, and the worst part isn't the bug — it's that the system knew. "You found the bug and documented it but didn't fix it?" is the angriest sentence in code review, and it's earned.

Agents drift into bug-documentation mode because finding feels like finishing: the analysis was the hard part, the writeup is the artifact, surely fixing is "a separate task." But a confirmed bug with a known root cause is the cheapest it will ever be to fix — the context is loaded, the repro is fresh, the fix is usually small. Deferring it throws that context away and converts a ten-minute fix into a future debugging session.

The sibling failure: the half-kept feature. Something gets built to 80%, has known gaps, and stays in the codebase as a "mostly works" zombie — too present to ignore, too broken to trust.

When to Use This Skill

  • An audit, review, or test wave just produced confirmed findings
  • You found a bug while working on something else and the instinct is "note it and stay on task"
  • A report you're writing contains "known issue," "TODO," or "should be fixed later"
  • A feature exists in a permanently-partial state — kept, but with gaps everyone routes around
  • The user asks "did you fix it or just document it?"

Don't use when: the "bug" is unconfirmed (a hunch needs verification before it earns a fix), the fix requires a product decision that genuinely belongs to the user, or you're mid-critical-path and a context switch would endanger the primary task — in those cases, defer explicitly (see step 3), don't just skip the skill.

Instructions

1. Confirm it's real, then treat the fix as part of the find

A finding's lifecycle is find → confirm → fix → verify, in one pass. The deliverable of an audit is not a list of bugs; it's a list of bugs that no longer exist, plus the residue that genuinely couldn't be fixed and why. Budget audits accordingly: an audit you only have time to half-fix is an audit you should scope smaller.

Read the full file on GitHub · 71 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. 9d ago First seen · 71 lines · 157 tokens per session scan A 8f9b5b93bb9e

Subscribe to this mod's changes

fix-it-now is a skill published in the GitHub repository mikestangdevs/craft-skills (4 stars, last pushed 3mo ago), licensed MIT. It adds 157 tokens to every session and 1,243 once invoked, about $0.0008 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.