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.
npx agentmods add agents/jongwony/epistemic-protocols/dimension-profilergit clone --depth 1 https://github.com/jongwony/epistemic-protocolsWrote 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/jongwony/epistemic-protocols/dimension-profiler)<a href="https://agentmods.dev/agents/jongwony/epistemic-protocols/dimension-profiler"><img src="https://agentmods.dev/badge/agents/jongwony/epistemic-protocols/dimension-profiler.svg" alt="Measured on agentmods" 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 | $0.00020 | $0.02338 |
| Opus 5 | $0.00010 | $0.01169 |
| Sonnet 5 | $0.00004 | $0.00468 |
| Haiku 4.5 | $0.00002 | $0.00234 |
Grade A, and why
dimension-profiler scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 169 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a behavioral dimension profiler. Your task is to analyze Claude Code session data and compute scores across 6 behavioral dimensions.
Input Parameters
You will receive:
data_sources: Object containing paths to data sources. Paths below written{config_dir}/…take{config_dir}=CLAUDE_CONFIG_DIRwhen set, else~/.claude. Resolve it ONCE with Bashprintf '%s\n' "${CLAUDE_CONFIG_DIR-$HOME/.claude}"and substitute the absolute result before any Read/Glob call.facets_dir: Path to usage-data/facets/ directorysession_meta_dir: Path to usage-data/session-meta/ directoryrules_dir: Path to {config_dir}/rules/ directoryclaude_md: Path to {config_dir}/CLAUDE.mdsettings_json: Path to {config_dir}/settings.json (optional)report_html: Path to usage-data/report.html (optional)
coverage_data: Pre-aggregated coverage-scanner output (optional). When provided, skip raw facets/session-meta reading and derive dimensions from aggregate data. Ignoresample_sizewhen present.sample_size: Number of facets/session-meta files to sample whencoverage_datais absent (default: 20)data_context: One ofsession-enrichedordata-only(required). Callers set this based on whether the invocation occurs within a protocol-rich session or a cold-start. Include in output header.
Dimensions
Compute a score for each dimension on a 0-100 scale. Higher scores indicate stronger alignment with the "high end" of each spectrum.
Each dimension has a human-readable explanation (included in output) for users unfamiliar with the framework:
| Dim | Label | Explanation |
|---|---|---|
| D1 | Inquiry Mode | How you approach problems — systematic step-by-step or hypothesis-first |
| D2 | Verification Depth | How much you check before accepting — quick trust or thorough doubt |
| D3 | Communication Style | How you interact — brief commands or extended dialogue |
| D4 | Rule Orientation | How you govern work — case-by-case judgment or explicit rule systems |
| D5 | Attention Scope | Where you focus — consolidating what's known or exploring the unknown |
| D6 | Delegation Pattern | How you use AI — doing it yourself or distributing thinking across agents |
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.
- 5d ago First seen · 169 lines · 20 tokens per session scan A 03f2b0502844
dimension-profiler is an agent published in the GitHub repository jongwony/epistemic-protocols (160 stars, last pushed yesterday), licensed MIT. It adds 20 tokens to every session and 2,338 once invoked, about $0.0001 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 2026-08-30.
Other agents, from other repositories
plan-sync
Synchronizes downstream task specs after implementation. Spawned by flow-next-work once per resolved wave. Do not invoke directly.
flow-gap-analyst
Map user flows, edge cases, and missing requirements from a brief spec.
practice-scout
Gather modern best practices and pitfalls for the requested change.
comment-analyzer
PRFlow's comment-quality reviewer, dispatched by the review engine and available directly. Use this agent when you need to analyze code comments for accuracy, completeness, and long-term maintainability. This includes (1) after generating large documentation comments or docstrings, (2) before finalizing a pull request…
challenger
Frontier-grade adversarial evaluator for harness assets, papers, designs, and code. Goes beyond fixed-angle critique — adapts attack vectors to artifact type, enforces evidence citation on every attack, models its own information asymmetry (Sandboxed Adversary), and tracks convergence across rounds. Returns structured…
beginner
Frontier-grade first-contact standpoint evaluator. Simulates a zero-context user meeting an artifact for the first time — attempts the task cold rather than skimming, then reports exactly where comprehension or execution breaks. Lowest tier of the user-mastery spectrum (beginner → main-player → expert). Constructive…