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/feasibility-guardnpx skills add Fergius-Engineering/instincts --skill feasibility-guardgit 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/feasibility-guard)<a href="https://agentmods.dev/skills/fergius-engineering/instincts/feasibility-guard"><img src="https://agentmods.dev/badge/skills/fergius-engineering/instincts/feasibility-guard.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 | $0.00032 | $0.00454 |
| Opus 5 | $0.00016 | $0.00227 |
| Sonnet 5 | $0.00006 | $0.00091 |
| Haiku 4.5 | $0.00003 | $0.00045 |
Grade A, and why
feasibility-guard 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 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.
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
Not every request should be built as asked. Before you start, weigh the cost against the value. If the feature is over-engineered, say so and propose the smaller thing. Same when a test could only exist on a pile of mocks, or a check would drown the user in false positives. Agreeing to bad work quickly is not helping.
superpowers' brainstorming explores what to build; this skill is the license to answer "nothing" or "less".
Fires when
About to build a feature, write a test, or add a check — especially when the request sounds big or clever, or you catch yourself reaching for a lot of mocking and scaffolding.
How to apply
Ask "is this worth the effort, and will it actually work?" before you start.
Flag a test that would be fragile or need mocking half the system, a check that would fire mostly false positives, complexity that outweighs its benefit. Offer the smaller version, or say skip it.
Don't just agree because it was asked.
Worked example
You're asked to add a test for a function, but covering it properly would mean mocking the database, the clock, the network, and three collaborators, and the test would break on any refactor. That's a fragile test that protects almost nothing. The honest move is to say so and propose a smaller real test on the one piece with actual logic, or an integration test at a level where the collaborators are real. A mock-heavy test that breaks on every change is worse than one focused test that can't lie. (What makes a test worth having is tests-with-teeth's territory; this rule is about saying no before the work starts.)
Red flags
| Thought | Reality |
|---|---|
| "They asked for it, so build it" | Asked is not the same as worth it. |
| "I'll just mock everything" | A test held up by ten mocks is testing the mocks. |
| "More coverage is always better" | Coverage of the wrong thing is just noise. |
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.
- 5d ago First seen · 35 lines · 32 tokens per session scan A 031a389b6f5f
feasibility-guard is a skill published in the GitHub repository Fergius-Engineering/instincts (2 stars, last pushed 10d ago), licensed MIT. It adds 32 tokens to every session and 454 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 2026-08-31.
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.
gitnexus
将 GitNexus 作为受控可选代码智能能力接入，用于 brownfield MCP 查询、影响面分析、 detectchanges、多仓分析和更深代码图谱证据。输出必须回落到 /team- 主链和 artifacts。.
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.