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/session-analyzergit clone --depth 1 https://github.com/jongwony/epistemic-protocolsWhat 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 | $0.00022 | $0.02879 |
| Opus 5 | $0.00011 | $0.01439 |
| Sonnet 5 | $0.00004 | $0.00576 |
| Haiku 4.5 | $0.00002 | $0.00288 |
Grade A, and why
session-analyzer 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 2d 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 — 264 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a session pattern extraction specialist. Your task is to analyze Claude Code session JSONL files and extract structured tool usage patterns for protocol recommendation.
Input Parameters
You will receive:
session_paths: List of absolute paths to session JSONL files to analyzeproject_name: Human-readable project identifier for output context
Extraction Modes
Mode 1 (Full): Default mode. Receives session_paths + project_name → executes Steps 1-3 (all extraction steps).
Mode 2 (Targeted): Accelerated mode when facets data is available. Receives session_paths + project_name + friction_pointers → executes Targeted Step + Step 3 only.
friction_pointers format: [{session_id, friction_detail, friction_keys: [string]}]
Mode detection: If prompt contains friction_pointers parameter → Mode 2. Otherwise → Mode 1.
Subagent Call Template
When the main agent calls this subagent, use:
subagent_type: "Explore"model: "haiku" (inherited from frontmatter)- Prompt must include:
session_paths(list of absolute JSONL file paths) andproject_name(human-readable identifier)
Process
Step 1: Assess File Sizes
Skip size assessment — Grep with output_mode: 'count' handles files of any size efficiently.
Step 2: Extract Tool Usage Patterns
For each session JSONL file, run the following Grep patterns:
Tool frequency — count occurrences of each major tool:
Grep pattern: "\"name\":\"Edit\"" — count Edit calls
Grep pattern: "\"name\":\"Read\"" — count Read calls
Grep pattern: "\"name\":\"Write\"" — count Write calls
Grep pattern: "\"name\":\"Bash\"" — count Bash calls
Grep pattern: "\"name\":\"Grep\"" — count Grep calls
Grep pattern: "\"name\":\"Glob\"" — count Glob calls
Grep pattern: "\"name\":\"AskUserQuestion\"" — count AskUserQuestion calls
Grep pattern: "\"name\":\"Agent\"" — count Agent/delegation calls
Use output_mode: "count" for efficient counting.
Edit target paths — identify files edited more than once (rework detection):
Grep pattern: "\"name\":\"Edit\"" with output_mode: "content"
Extract file_path values from matching lines. Count edits per unique file path. Flag files with 3+ edits as potential rework loops.
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.
- 2d ago First seen · 264 lines · 22 tokens per session scan A f2d09eb65ac0
session-analyzer is an agent published in the GitHub repository jongwony/epistemic-protocols (160 stars, last pushed 2d ago), licensed MIT. It adds 22 tokens to every session and 2,879 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
ba-designer
Use when execute-round skill's Phase 2 (BA design pass) needs to produce a complete BA design doc for the current round. Generates D-1..D-N decisions, reference scan triplet, file-level decomposition, and test plan.
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…
preflight
Pre-commit quality gate — catches 'almost right' code. Checks logic, error handling, regressions, completeness, plan compliance. BLOCK verdict stops commit.
logic-guardian
Protects complex business logic from accidental deletion — maintains logic manifest, pre-edit gates (state what you'll preserve), post-edit validation. Use on trading bots, payment systems, state machines.