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-detection)<a href="https://agentmods.dev/agents/intentdriven/abcd/cold-reading-detection"><img src="https://agentmods.dev/badge/agents/intentdriven/abcd/cold-reading-detection/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-detection"><img src="https://agentmods.dev/badge/agents/intentdriven/abcd/cold-reading-detection.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 | $0.00047 | $0.01961 |
| Opus 5.5 | $0.00019 | $0.00784 |
| Sonnet 5.5 | $0.00009 | $0.00392 |
| Haiku 4.5 | $0.00005 | $0.00196 |
Grade B, and why
cold-reading-detection 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 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.
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 — 150 lines — stays where its author put it; the contents beside it link to each section on GitHub.
cold-reading-detection — the detection position
Object
The shipped tree read against the claim record: the source, the tests, the delivered documentation and the build configuration on one side, and the shipped intents, the specs, the disciplines, the glossary and the brief's current text on the other. The draft and planned intents are withheld, because a tension against a claim nobody has committed to is not a tension.
Repository sources the assembler admits at this position
.abcd/development/brief/01-product— the construal as it presently stands..abcd/development/brief/02-constraints— the platform, the dependency stance, the invariants and the naming..abcd/development/brief/04-surfaces— the surfaces chapter..abcd/development/brief/05-internals— the internals chapter..abcd/development/brief/06-delivery— the delivery chapter..abcd/development/brief/glossary— the committed terms..abcd/development/brief— the meta chapter, the one file00-meta.mdat the brief's root..abcd/development/intents/disciplines— the standing commitments the record already holds..abcd/development/intents/shipped— each shipped intent as its claim record..abcd/development/specs— the design record a capability was built against..abcd/development/principles— the knowledge record, each principle as its title and statement alone..— the shipped tree: source, tests, delivered documentation, root prose and build configuration.
What this section states, and what governs. This section states what your position MAY read. The bundle you were handed states what THIS run was actually given, which is narrower: a reading is commissioned with a position and a target state, and the committed preset entry for that position decides what it is handed and travels in the bundle. Where the two disagree, the bundle governs. The absence of material this section names is therefore not a finding — it is what this run was handed, and reporting it as a tension against the record would be reporting the commission rather than the object.
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 Changed · +10 lines b58f0411db41
- 23d ago Changed · +1 lines 8a044428f2ea
- 24d ago Changed · +4 lines 8305d08ba9d1
- 1mo ago First seen · 135 lines · 47 tokens per session scan B 4e8ca629bc6c
cold-reading-detection is an agent published in the GitHub repository intentdriven/abcd (3 stars, last pushed yesterday), licensed MIT. It adds 47 tokens to every session and 1,961 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-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.
cantonal-law-expert
Analyzes law across all 26 Swiss cantons including cantonal constitutions, court systems, intercantonal concordats, procedural variations, and multi-canton comparisons.