fast-agent is a command-line framework for creating, running, and evaluating AI agents and workflows, including connections to models, skills, and MCP servers. It is used by developers building coding tools, multimodal agents, automations, and evaluation workflows.
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 skills/evalstate/fast-agent/session-investigatornpx skills add evalstate/fast-agent --skill session-investigatorgit clone --depth 1 https://github.com/evalstate/fast-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/evalstate/fast-agent/session-investigator)<a href="https://agentmods.dev/skills/evalstate/fast-agent/session-investigator"><img src="https://agentmods.dev/badge/skills/evalstate/fast-agent/session-investigator.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 | $0.00068 | $0.02292 |
| Opus 5 | $0.00034 | $0.01146 |
| Sonnet 5 | $0.00014 | $0.00458 |
| Haiku 4.5 | $0.00007 | $0.00229 |
Grade A, and why
session-investigator 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 — 229 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Session Investigator
Diagnose fast-agent session issues by examining session and history files.
Session Directory Structure
Sessions are stored in .fast-agent/sessions/<session-id>/:
2601181023-Kob2h3/
├── session.json # Session metadata
├── history_<agent>.json # Current agent history
└── history_<agent>_previous.json # Previous save (rotation backup)
Session IDs encode creation time: YYMMDDHHMM-<random> (e.g., 2601181023 = 2026-01-18 10:23).
Key Files
session.json
{
"name": "2601181023-Kob2h3",
"created_at": "2026-01-18T10:23:24.116526",
"last_activity": "2026-01-18T10:39:42.873467",
"history_files": ["history_dev_previous.json", "history_dev.json"],
"metadata": {
"agent_name": "dev",
"first_user_preview": "is it possible to override..."
}
}
history_.json
{
"messages": [
{
"role": "user|assistant",
"content": [{"type": "text", "text": "..."}],
"tool_calls": {"<id>": {"method": "tools/call", "params": {"name": "...", "arguments": {}}}},
"tool_results": {"<id>": {"content": [...], "isError": false}},
"channels": {
"fast-agent-timing": [{"type": "text", "text": "{\"start_time\": ..., \"end_time\": ..., \"duration_ms\": ...}"}],
"fast-agent-tool-timing": [{"type": "text", "text": "{\"<tool_id>\": {\"timing_ms\": ..., \"transport_channel\": ...}}"}],
"reasoning": [{"type": "text", "text": "..."}]
},
"stop_reason": "endTurn|toolUse|error",
"is_template": false
}
]
}
Investigation Commands
Basic inspection
# Message count
jq '.messages | length' history_dev.json
# Last N messages overview
jq '.messages[-5:] | .[] | {role, stop_reason, has_tool_calls: (.tool_calls != null), has_tool_results: (.tool_results != null)}' history_dev.json
# View specific message
jq '.messages[227]' history_dev.json
Tool call correlation
Tool calls and results are linked by correlation ID. Valid pattern: assistant with tool_calls → user with matching tool_results.
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 · 229 lines · 68 tokens per session scan A d8df6fafb1dc
session-investigator is a skill published in the GitHub repository evalstate/fast-agent (3,910 stars, last pushed today), licensed Apache-2.0. It adds 68 tokens to every session and 2,292 once invoked, about $0.0003 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 skills, from other repositories
hive.browser-automation
Required before any hive-browser CLI command. The browser is driven from the terminal by running hive-browser ... --json via terminalexec — not via MCP tools. Teaches the browser lifecycle rules (the bridge attaches to the USER'S running Chrome — never kill or launch browser processes; timeouts are transport issues…
hive.slack-notifications-setup
Set up a Slack notification channel (Sentinel) for a colony by driving the browser — reuse or create the "Hive Sentinel" Slack app from a JSON manifest, install it, capture the bot + app tokens, create/select the channel via the Slack API, and turn Sentinel on so the colony can ping the user on Slack and accept…
hive.chart-creation-foundations
Required reading whenever any chart tool is available. Teaches the one-tool embedding contract (call chartrender → live chart appears in chat AND a downloadable PNG lands in the queen session dir), the ECharts (data viz) vs Mermaid (structural diagrams) decision, the BI/financial-grade aesthetic baseline (no…
browser-edge-cases
SOP for debugging browser automation failures on complex websites. Use when browser tools fail on specific sites like LinkedIn, Twitter/X, SPAs, or sites with Shadow DOM.
hive.pdf
Read, write, merge, split, rotate, watermark, encrypt, and OCR PDF files using Python (pypdf, pdfplumber, reportlab, pypdfium2) and command-line tools (poppler-utils, qpdf). Use when the user asks to extract text/tables/images from a PDF, create or modify a PDF, combine or split PDFs, OCR a scanned PDF…
triage-issue
Analyze a GitHub issue, verify claims against the codebase, and close invalid issues with a technical response.