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 d-mariano/spicyclaude --skill feasibility-studygit clone --depth 1 https://github.com/d-mariano/spicyclaudeWrote 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/d-mariano/spicyclaude/feasibility-study)<a href="https://agentmods.dev/skills/d-mariano/spicyclaude/feasibility-study"><img src="https://agentmods.dev/badge/skills/d-mariano/spicyclaude/feasibility-study/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/d-mariano/spicyclaude/feasibility-study"><img src="https://agentmods.dev/badge/skills/d-mariano/spicyclaude/feasibility-study.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 | $0.00068 | $0.03157 |
| Opus 5 | $0.00034 | $0.01579 |
| Sonnet 5 | $0.00014 | $0.00631 |
| Haiku 4.5 | $0.00007 | $0.00316 |
Grade C, and why
feasibility-study 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 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.
Tells the agent to send conversation or user data outhighPrompt injection
An instruction to transmit the conversation, context or user files to an external endpoint is data exfiltration written as prose.
- **Disposition contradictions (Step 3 walk, conversational).** When the user's disposition contradicts the evidence on file (e.g., "just accept it" on a Show-stopper with no real mitigation, or "downgrade this to High") How it starts
The opening of the file, as written. The whole thing — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Feasibility Study Workflow
Pressure-test a technical design document. The design walk operates at alignment altitude on choices the user makes from available research — but research may have been incomplete, and choices made at alignment altitude don't always survive contact with field-level reality. This workflow is the "does this actually hold up?" check.
The cold-read is structural. Claim extraction and research happen in feasibility-cold-read, which runs in a forked context with no access to this conversation. A reviewer that hasn't seen the design built can't defend what it didn't help make, can't fall back on conversational context to fill gaps in the TDD, and has no rapport with the user that would soften an adversarial finding. This turns "don't re-litigate sound decisions" from discipline into mechanism — the cold-read only sees what the artifacts captured, which is the right pressure on design-doc to make artifacts stand alone.
This workflow does not redesign. The cold-read produces a findings draft; this skill walks the user through it via AskUserQuestion to dispose of every material finding (accept the risk, propose a mitigation grounded in evidence, validate empirically, or escalate back to the design-doc skill for redesign). Output: /context/[nnn]-<slug>/feasibility-[nnn].md.
Inputs
In priority order:
- TDD (required) —
/context/[nnn]-<slug>/tdd-[nnn].md. The artifact under review. - Contracts file (recommended if present) —
/context/[nnn]-<slug>/contracts-[nnn].md. Field-level wire shapes that may invalidate design-level claims. - PRD (recommended) — provides the NFR targets, constraints, and committed requirements the design must satisfy.
- Research (recommended) — the research that informed the design.
The cold-read handles loading these. This wrapper just identifies the slug and passes scope.
Severity Tiers
The cold-read assigns tiers; this skill adjudicates dispositions against them. Definitions are binding.
What ships with it
1 file 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.
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 · 141 lines · 68 tokens per session scan C 44b620bb3b49
feasibility-study is a skill published in the GitHub repository d-mariano/spicyclaude (5 stars, last pushed 1mo ago), licensed MIT. It adds 68 tokens to every session and 3,157 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it C with 1 finding (tells the agent to send conversation or user data out). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
rework-rate
Measure and interpret PR rework rate — the emerging 5th DORA metric.
omh-code-review
This is a Hermes-native code-review workflow skill.
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
code-reviewer
Code review specialist focused on patterns, bugs, security, and performance.
agent-teams-simplify-and-harden
Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find complexity, security gaps, and spec deviations, then loops until code compiles cleanly, all tests pass, and auditors find zero issues or…