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 agentmods add skills/fergius-engineering/instincts/fix-the-root-causenpx skills add Fergius-Engineering/instincts --skill fix-the-root-causegit clone --depth 1 https://github.com/Fergius-Engineering/instinctsWrote 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/fergius-engineering/instincts/fix-the-root-cause)<a href="https://agentmods.dev/skills/fergius-engineering/instincts/fix-the-root-cause"><img src="https://agentmods.dev/badge/skills/fergius-engineering/instincts/fix-the-root-cause.svg" alt="Measured on agentmods" 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 | $0.00025 | $0.00387 |
| Opus 5 | $0.00013 | $0.00193 |
| Sonnet 5 | $0.00005 | $0.00077 |
| Haiku 4.5 | $0.00003 | $0.00039 |
Grade A, and why
fix-the-root-cause 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 4d 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.
What it actually says
The rule
The place a bug shows up is rarely the place it comes from. Patching the symptom at the surface leaves the real cause free to break something else next week. Find the layer that produced the bad state and fix it there.
This sharpens superpowers' systematic-debugging: that skill finds the bug; this one decides which layer the fix belongs in.
Fires when
Any bug fix, especially a crash, a null, a corrupt value, or a wrong result that shows up far from where the data was created.
How to apply
Trace the bad value back to where it was born, not just where it blew up. Ask "what let this state exist in the first place?" and fix that.
A guard at the call site is fine as a seatbelt, but it isn't the fix if something upstream keeps handing out broken state.
Worked example
A page crashes on user.address.city because address is null. The symptom fix is a null check on the page. But the real cause is the user loader, which returns a half-built user when a join fails, so any page that touches address is one click from the same crash. Fixing the loader to either return a complete user or fail loudly kills the whole class of crashes. The null check alone just moves the next crash to a different page.
Red flags
| Thought | Reality |
|---|---|
| "A null check here makes it stop crashing" | It stops this crash, not the cause. |
| "The bug is on this page" | The bug is wherever the bad value was made. |
| "I'll patch the symptom now and fix it properly later" | Later rarely comes, and the bad state keeps spreading. |
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.
- 4d ago First seen · 33 lines · 25 tokens per session scan A aacfffbf4849
fix-the-root-cause is a skill published in the GitHub repository Fergius-Engineering/instincts (2 stars, last pushed 10d ago), licensed MIT. It adds 25 tokens to every session and 387 once invoked, about $0.0001 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
rulesync
Generates and syncs AI rule configuration files (.cursorrules, CLAUDE.md, copilot-instructions.md) across 20+ coding tools from a single source. Use when syncing AI rules, running rulesync commands, importing or generating rule files, or managing shared AI coding configurations.
establishing-project-context
Use when the user asks to establish shared project language, or project work exposes a conflicting, renamed, or deprecated domain term that needs active semantic modeling. Routine small tasks stay on the fast path.
autoprompt
Explicit-only useful-first orchestration. Invoke /autoprompt to turn a mission into one executable roadmap, build dependency-safe lanes, and verify the result with independent reviewers. Never infer invocation from ordinary requests. Never resume from leftover artifacts without an explicit resume instruction.
loop
Full execution protocol for MODE: LOOP — the compound-engineering loop: brainstorm → plan → build → review → improve, iterating under defense-in-depth stop conditions with generator/critic separation, durable resumable state, and mandatory compounding learning capture. Loaded on demand by the architect when the loop…
restore-internals-seams-in-finally-blocks-after-each-test
When delegating a task affected by this skill, include.
loongsuite-pilot-insight
基于 LoongSuite Pilot / AI Coding Agent 日志生成事件洞察、组织洞察、数据质量、研发效能和 AI Native 使用类 SLS 报表时使用；包含 AI Coding 事件表语义，以及团队报表可选的部门维表、deptuser 组织关系、指标口径和公共 CTE，通常与 sls-dashboard-builder 一起使用。.