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.
npx skills add mikestangdevs/craft-skills --skill fix-it-nowgit clone --depth 1 https://github.com/mikestangdevs/craft-skillsWrote 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/skills/mikestangdevs/craft-skills/fix-it-now)<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.
<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>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 | $0.00157 | $0.01243 |
| Opus 5 | $0.00078 | $0.00622 |
| Sonnet 5 | $0.00031 | $0.00249 |
| Haiku 4.5 | $0.00016 | $0.00124 |
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.
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.
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.
- 9d ago First seen · 71 lines · 157 tokens per session scan A 8f9b5b93bb9e
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.
Other skills, from other repositories
plumb-line-remediate
Use when applying findings from a plumb-line audit report — the builder has a report (or pasted findings) and wants the fixes made. Opt-in and separate from the audit, which is read-only and never fixes.
craft-fix
The Craftsman standard for driving fixes against an existing craft-audit workspace — "fix the findings", "fix SEC-003", "work through the audit", "start the climb". An ACTION skill, not a domain: it picks findings off the master tracker's climb sequence, re-verifies each is still real, gets the user's approval, and…
recipe-diagnose
Investigate problem, verify findings, and derive solutions.
audit
Project health audit and health check — architecture, performance, tests, dependencies, code quality. Use when assessing overall project health, before releases, or after refactors.
investigate
Investigate bugs and errors in Elixir/Phoenix — root-cause analysis for crashes, exceptions, stack traces, test failures. Use --parallel for deep 4-track investigation.
narrow-bare-rescue
Narrow bare rescue in Elixir so real errors like KeyError and typos propagate instead of being swallowed. Use to audit rescues and refactor error handling.