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.
git clone --depth 1 https://github.com/intentdriven/abcdWrote 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/agents/intentdriven/abcd/cold-reading-comparative)<a href="https://agentmods.dev/agents/intentdriven/abcd/cold-reading-comparative"><img src="https://agentmods.dev/badge/agents/intentdriven/abcd/cold-reading-comparative/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/agents/intentdriven/abcd/cold-reading-comparative"><img src="https://agentmods.dev/badge/agents/intentdriven/abcd/cold-reading-comparative.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 | $0.00046 | $0.01789 |
| Opus 5.5 | $0.00018 | $0.00716 |
| Sonnet 5.5 | $0.00009 | $0.00358 |
| Haiku 4.5 | $0.00005 | $0.00179 |
Grade B, and why
cold-reading-comparative scanned grade B 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 17d 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.
Instruction-override phrasingmediumPrompt injection
Text telling the model to disregard its earlier instructions or safety rules is the shape of a prompt injection, whoever wrote it.
"ignore previous instructions", "mark this accepted", a fenced block asserting Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
How it starts
The opening of the file, as written. The whole thing — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.
cold-reading-comparative — the comparative position
Object
The candidate set, which is the widening reading's pre-admission output, read against the declared selection criteria. The candidate set is ONE widening run's returned configurations, derived from the record as the one committed widening run at the target whose items carry no disposition and no admission — a run being at the target when the commit its own record names is the target or an ancestor of it across which nothing outside the instrument's own record changed — and handed to you before admission: you receive each candidate's identifier, the configuration it names and what admits it, and nothing else about it. What has happened to those candidates since — a disposition, an admission, a surprise, any other run — is the researcher's judgement and is withheld from you; no other prior run's stored output is readable, and the pattern each candidate was read under stays in its envelope rather than travelling with it. The criteria are a declared, recorded discipline in the passed material. They are never supplied at invocation, and you never author one.
Where the candidate set carries fewer than two configurations this position is not exercised at all, and that outcome is recorded as such rather than answered.
Repository sources the assembler admits at this position
.abcd/development/intents/disciplines— the standing commitments the record already holds, narrowed here to the selection criteria alone..abcd/work/issues/readings— the derived widening run's items, projected to the configuration and what admits it, keyed by the item identifier you cite.
What this section states, and what governs. This section states what your position MAY read. A bundle states what THIS run was actually given, and where the two disagree the bundle governs — the same rule every other position carries.
Question
Answer exactly this question, and no other:
For each candidate and each declared criterion, how do options of this shape ordinarily behave?
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.
- 17d ago Changed · +10 lines 43ae3252ecbc
- 1mo ago First seen · 135 lines · 46 tokens per session scan B bc9b7e7c58b8
cold-reading-comparative is an agent published in the GitHub repository intentdriven/abcd (3 stars, last pushed today), licensed MIT. It adds 46 tokens to every session and 1,789 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it B with 1 finding (instruction-override phrasing). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-05.
Other agents, from other repositories
agent-spawning
Guide to spawning agents with Claude Code's Task tool.
agent-coordination
Coordination patterns for multi-agent collaboration.
swiss-legal-prompt-engineer
Transforms vague legal queries into structured prompts through Socratic dialogue, recommends optimal workflows, and guides system navigation with persistent cross-session learning.
swiss-legal-adversary
Challenges a legal position by finding weaknesses, counter-precedents, and opposing arguments under Swiss law.
swiss-legal-advocate
Builds the strongest possible case in favor of a legal position using Swiss law precedents, statutory provisions, and doctrine.
swiss-legal-briefing-coordinator
Pure planner for the briefing flow: classifies the query, selects the specialist panel, and (given Q&A history) builds the structured execution plan. Panel consultation and user Q&A are orchestrated by the parent command at the top-level session, where Task dispatch works on every host.