Borrowing it
Nothing to install: this file belongs to safety-quotient-lab/psychology-agent. 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/safety-quotient-lab/psychology-agent/main/.claude/skills/knock/SKILL.mdgit clone --depth 1 https://github.com/safety-quotient-lab/psychology-agentWrote 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/safety-quotient-lab/psychology-agent/knock)<a href="https://agentmods.dev/skills/safety-quotient-lab/psychology-agent/knock"><img src="https://agentmods.dev/badge/skills/safety-quotient-lab/psychology-agent/knock/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/safety-quotient-lab/psychology-agent/knock"><img src="https://agentmods.dev/badge/skills/safety-quotient-lab/psychology-agent/knock.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 | $0.00017 | $0.01783 |
| Opus 5.5 | $0.00007 | $0.00713 |
| Sonnet 5.5 | $0.00003 | $0.00357 |
| Haiku 4.5 | $0.00002 | $0.00178 |
Grade A, and why
knock 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 — 185 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Knock — Single-Option Effect Tracing
Trace the effects of ONE option, change, or decision through 10 orders of
knock-on analysis. This skill produces the evidence that /adjudicate uses
when comparing multiple options — but it runs independently for single-option
analysis, impact assessment, or pre-decision exploration.
/knock = trace effects of ONE option/change through 10 orders
/adjudicate = 2-pass /knock on EACH option → compare → resolve
Arguments
Parse $ARGUMENTS to determine scope:
| Argument | Behavior |
|---|---|
| (empty) | Identify the change or option from conversation context |
[topic] |
Trace knock-on effects for the named change |
inline |
Abbreviated: 4 orders + structural scan (7–10) |
full |
Full depth: all 10 orders elaborated |
Default depth: infer from apparent scale. Small/tactical changes → inline.
Architecture decisions, policy changes, or anything affecting multiple files → full.
Protocol
Step 1: State the Change
One sentence describing the specific change being traced. Not vague ("improve X") — concrete ("add route Y to worker.js" or "extend depth from 8 to 10 orders").
Step 2: Classify the Domain
| Domain | Signal | Primary effect vectors |
|---|---|---|
| Code | file changes, API surfaces, dependencies | builds → tests → deploys → users |
| Data | schema, model, training data changes | pipeline → scores → downstream consumers |
| Pipeline | CI/CD, build, deploy changes | reliability → velocity → trust |
| Infrastructure | hosting, transport, networking | availability → latency → cost |
| UX | interface, accessibility, communication | perception → adoption → feedback |
| Operational | process, workflow, documentation | velocity → consistency → knowledge |
| Product | features, scope, direction | users → market → mission alignment |
Step 3: Ground the Analysis
Before tracing orders, verify actual dependencies:
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 · 185 lines · 17 tokens per session scan A dead924a0f6b
knock is a skill published in the GitHub repository safety-quotient-lab/psychology-agent (23 stars, last pushed 6mo ago), licensed Apache-2.0. It adds 17 tokens to every session and 1,783 once invoked, about $0.0001 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 2026-08-30.
knock compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| knocksafety-quotient-lab/psychology-agent | Skill | 23 | 6mo ago | Apache-2.0 | A | 17 | Claude Code |
| goutoujunshishengjidaguai-china/goutoujunshi | Skill | 9.3k | 1mo ago | MIT | A | 175 | Codex |
| game-selectionkangarooking/cangjie-skill | Skill | 12k | 1mo ago | MIT | A | 134 | Claude Code, Codex |
| satoriMetcalfSolutions/Satori | Skill | 116 | 4d ago | Apache-2.0 | A | 107 | Claude Code |
| compatibilitygeeks-accelerator/in-bed-ai | Skill | 26 | today | MIT | A | 51 | Claude Code |
| personality-personalitygeeks-accelerator/in-bed-ai | Skill | 26 | today | MIT | A | 57 | Claude Code |
| cialdini-influencefatihguner/foreman | Skill | 63 | 2mo ago | MIT | A | 88 | Claude Code |