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 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/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/evalstate/fast-agent/session-investigator"><img src="https://agentmods.dev/badge/skills/evalstate/fast-agent/session-investigator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00068 | $0.02292 |
| Opus 5.5 | $0.00027 | $0.00917 |
| Sonnet 5.5 | $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 1mo 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.
- 1mo 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 (3,943 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 5.5. 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
review-efficiency
Skill "review-efficiency" from dhaupin/vant, covering efficiency review, the question, what to check, 1. compute and 2. network.
audit-deploy
Skill "audit-deploy" from dhaupin/vant, covering deploy audit, the question, what to check, 1. build and does build pass?.
audit-reliability
Skill "audit-reliability" from dhaupin/vant, covering reliability, the question, what to check, 1. graceful degradation and 2. recovery.
review-performance
Skill "review-performance" from dhaupin/vant, covering performance review, rule #1, profile before you optimize, what to check and 1. time.
debugger
Skill "debugger" from dhaupin/vant, covering debugger, when to use, what to do, 1. start debugging and 2. common commands.
chain-full-audit
Complete system audit.