Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/agentii-ai/agentii-investment-intelligencenpx agentmods add skills/agentii-ai/agentii-investment-intelligence/specifyWrote 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/agentii-ai/agentii-investment-intelligence/specify)<a href="https://agentmods.dev/skills/agentii-ai/agentii-investment-intelligence/specify"><img src="https://agentmods.dev/badge/skills/agentii-ai/agentii-investment-intelligence/specify/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/agentii-ai/agentii-investment-intelligence/specify"><img src="https://agentmods.dev/badge/skills/agentii-ai/agentii-investment-intelligence/specify.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 | $0.00058 | $0.00371 |
| Opus 5 | $0.00029 | $0.00186 |
| Sonnet 5 | $0.00012 | $0.00074 |
| Haiku 4.5 | $0.00006 | $0.00037 |
Grade A, and why
specify 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 today.
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
agentii.specify
Creates a research thesis directory and its specification.
Hard rules
- Refuse creation while
constitution_pin: unratified(Q83 A+): no research may be produced under placeholder governance. Aggregate checks and staged orders hard-fail onunratified— a thesis created early could never be re-reviewed properly (no old constitution to diff against). - ID allocation is mkdir-as-CAS (Q27):
os.mkdir();FileExistsError→ increment and retry. Neverexist_ok=True. - Pillars are priority-ordered and independently falsifiable (Q30): P1 = the
Minimum Defensible View; every
wrong_ifis{metric, threshold, source}— prose is rejected (Q8 contract 4).
What it produces
theses/{nnn}-{slug}/
├── spec.md # pillar-prioritized (spec-template.md)
├── thesis.md # initialized living file (thesis-template.md)
└── checklists/thesis-quality.md # machine-maintained, bidirectional (Q32)
Invocation
python3 scripts/agentii_cmd.py specify --workspace /path/to/workspace --slug ai-semiconductors
Gate 1 (after specify, informational) shows pillar/wrong_if decidability.
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.
- today First seen · 40 lines · 58 tokens per session scan A 1ecdd102e26d
specify is a skill published in the GitHub repository agentii-ai/agentii-investment-intelligence (203 stars, last pushed today), licensed Apache-2.0. It adds 58 tokens to every session and 371 once invoked, about $0.0003 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 2026-09-09.
Other skills, from other repositories
prompt-architect
Create and optimize reusable prompt templates for AI assistants and autonomous agents. Use when user says "make a prompt for this task", "improve this prompt", "write a prompt template", "create a prompt for [task]", "optimize this prompt", or requests help designing instructions for LLMs or agents. Also trigger when…
coding-agent-prompt-generator
Generates optimised prompts for Claude Code sessions (Anthropic's agentic coding tool that works in your terminal, IDE, or desktop app). Use whenever the user wants to hand a coding, refactoring, debugging, migration, audit, research, or repo-maintenance task to Claude Code — even if they don't say "Claude Code"…
cowork-prompt-generator
Generates optimized prompts for Claude Cowork (Anthropic's autonomous file-based agent mode). Use whenever the user wants to delegate any file-based, document, or multi-step task to Cowork — even if they don't say "Cowork" explicitly. Triggers include: "I want a prompt for Cowork", "do this in Cowork", "help me set up…
draco-research-promptgen
Transform vague research requests into prompts that maximise deep research agent performance, based on the DRACO benchmark methodology.
bailii-case-download
Search BAILII (www.bailii.org) for a UK or Irish case and download the full judgment as a clean PDF. Use whenever the user wants a case from BAILII, gives a neutral citation (e.g. "[2024] EAT 114", "[2021] UKSC 5") or a BAILII URL and asks to fetch/download/save it, asks for "the full case as a PDF", wants to verify a…
quarry-parcels
Get parcel data on any property — owner, mailing address, absentee flag, zoning, units, year built, sqft, acreage, and value — from Bristol's Quarry engine. This is the default way to answer ANY "who owns this," "pull the parcel," "what's the zoning," "what's it worth," or property-owner question. No map, no key, no…