Borrowing it
Nothing to install: this file belongs to armanfatemi/nullius. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/armanfatemi/nullius/main/.claude/skills/intent-to-proposal/SKILL.mdgit clone --depth 1 https://github.com/armanfatemi/nulliusWrote 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/armanfatemi/nullius/intent-to-proposal)<a href="https://agentmods.dev/skills/armanfatemi/nullius/intent-to-proposal"><img src="https://agentmods.dev/badge/skills/armanfatemi/nullius/intent-to-proposal/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/armanfatemi/nullius/intent-to-proposal"><img src="https://agentmods.dev/badge/skills/armanfatemi/nullius/intent-to-proposal.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 7 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Prompt Injection · line 220 Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.
- medium Agent Snooping · line 12 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
- medium Agent Snooping · line 87 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
- medium Agent Snooping · line 314 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
- medium Agent Snooping · line 345 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
- medium Excessive Agency · line 182 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Prompt Injection · line 447 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
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 | $0.00087 | $0.07846 |
| Opus 5.5 | $0.00035 | $0.03138 |
| Sonnet 5.5 | $0.00017 | $0.01569 |
| Haiku 4.5 | $0.00009 | $0.00785 |
Grade A, and why
intent-to-proposal 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 2mo 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 — 529 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Idea → OpenSpec Proposal
This skill turns a rough idea into a well-scoped, implementation-ready OpenSpec proposal (or set of proposals). Proposals generated without a codebase survey produce under-specified artifacts that cost a full refinement iteration in Stage 2 — closing that gap is why this skill exists.
Boundary with openspec-propose
This repo also has .claude/skills/openspec-propose/SKILL.md — a real, separate tool, not a duplicate of this one. Do not chain into it from here. It takes a change name or a short description, runs openspec new change, and walks the openspec CLI's own schema-driven loop (openspec status, openspec instructions) to fill in the generic template for proposal.md / design.md / tasks.md. That is the right tool when the shape of the change is already decided and what's needed is the paperwork; this skill writes richer artifacts directly, using this repo's enriched templates below, precisely for the case where the shape is not yet decided.
intent-to-proposal owns the opposite case: the idea is still raw. Its phases — the Phase 1 dialogue, the Phase 2 codebase survey, the Phase 3 devil's-advocate refutation, the Phase 4 decomposition call — are the actual work; Phase 5's artifacts are the output of that work, not a template fill-in. If a request already reads like a settled, scoped change, use openspec-propose. If it is a rough problem statement, a symptom, or "figure out what to build," use this skill — the survey-then-refute loop is what openspec-propose's straight-line template loop does not do.
Entry conditions — adapt when you're not starting cold
The phases below assume a cold start from a raw idea. In practice the skill is often invoked mid-session, after work that already did some of Phase 1–2. Adapt rather than redo:
- Continuation (already mid-investigation/debug). If the current session already root-caused a bug or surveyed the touched code, that work is your Phase 1 understanding and part of your Phase 2 survey — don't re-dispatch a redundant Explore over ground you've already covered. But still (a) run the Phase 2 active-changes cross-check (
openspec/changes/) and the per-change-type red-flag check — both are easy to drop when reusing prior work — and (b) run the Phase 3 devil's advocate as a fresh agent. The prior investigation carries the most context bias, so the independent critic matters more, not less. - Idea sourced from a detailed task description. Phase 1 may legitimately produce zero
AskUserQuestionquestions — if the task already answers them, confirm understanding in prose and proceed. Zero questions is correct here, not a skipped phase. - Second idea in the same session. Each new idea gets its own full Phase 1–5. You MAY reuse a prior devil's advocate ONLY when the new idea is in the same architectural class as one already critiqued this session — and only if you say so and why. Otherwise dispatch a fresh one. Do not silently abbreviate the phases.
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.
- 2mo ago First seen · 529 lines · 87 tokens per session scan A 80f0c0cafd88
intent-to-proposal is a skill published in the GitHub repository armanfatemi/nullius (5 stars, last pushed 13d ago), licensed MIT. It adds 87 tokens to every session and 7,846 once invoked, about $0.0003 per session on Opus 5.5. 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
argot-setup
Set argot up for a repository end to end — audit its history, decide what should shape its voice, fit, verify the fit actually catches things, tune the rules its own history says are noisy, and wire the places it runs (pre-write hook, pre-commit, MCP, CI). One sitting, one decision at a time, each proposed with the…
argot-check
Score your working changes with argot — flag code foreign to this repo's own patterns (unfamiliar dependencies, APIs, constructs), functions the repo already has, code filed in the wrong place, imports that break the repo's layering, and tests weakened, disabled, or deleted alongside a production change — before…
argot-write-rule
Codify a repo convention argot's built-ins don't cover into a scripted custom rule — a .argot/rules/NAME/rule.toml manifest plus a sandboxed Rhai script that fires exactly like a built-in, gated on a green fixture suite before it ever sees a real diff. Use when the user asks to "write an argot rule for X", "codify…
argot-review-pr
Review a specific pull request (or diff range) against this repo's learned patterns with argot, without checking it out — flag dependencies, APIs, and constructs foreign to how the repo is written, duplicated functions, misfiled code, layering breaks, and tests weakened, disabled, or deleted alongside a production…
argot-refresh
Refresh Argot's committed fit snapshot safely — first diagnose why maintenance is recommended, re-audit corpus scope and structural path changes, review stale mutes and policy entries with the user, then fit locally, verify, and prepare the reviewed .argot/ update. Use when argot status, argot check, MCP, or CI…
argot-suggest-rules
Turn a convention argot has already discovered into a scripted custom rule. Runs argot conventions, surfaces the repo's mined placement conventions (where a kind of code lives — "validation in schema files", "DB access only in migrations", "business logic in the service layer, not views") and internal-API vocabulary…