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 jmagly/aiwg --skill session-exploregit clone --depth 1 https://github.com/jmagly/aiwgWrote 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/jmagly/aiwg/session-explore)<a href="https://agentmods.dev/skills/jmagly/aiwg/session-explore"><img src="https://agentmods.dev/badge/skills/jmagly/aiwg/session-explore/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/jmagly/aiwg/session-explore"><img src="https://agentmods.dev/badge/skills/jmagly/aiwg/session-explore.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 | $0.00025 | $0.01180 |
| Opus 5 | $0.00013 | $0.00590 |
| Sonnet 5 | $0.00005 | $0.00236 |
| Haiku 4.5 | $0.00003 | $0.00118 |
Grade A, and why
session-explore 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 today.
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 — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Explore Session History
Answer the user's question from the normalized aiwg sessions catalog. Start
from their topic, time window, provider, workspace, or known session; they do
not need to know catalog terminology. This is historical inspection, not the
singular aiwg session launcher or permission to replay recorded commands.
Scope and first reads
Use the current project when unambiguous. Preserve a supplied --db on every
call. Ask only when workspace identity, intended data scope, or a necessary
source is missing. Inspect aiwg sessions sources --json and
aiwg sessions doctor --json, then list the authorized workspace:
aiwg sessions list --workspace <workspace> --limit 50 --json
Check data.coverage before interpreting an empty result. Missing, stale,
export-required, rejected, or pending histories are gaps, not proof that no
activity occurred. Follow a concrete availability diagnostic; do not install
a runtime, scan shared provider roots, import histories, or broaden the
workspace merely to make a query succeed. If acquisition is requested, use the
acquisition recipe.
Choose the smallest useful query
Read the relevant recipes for exact supported filters:
| User need | Route |
|---|---|
| Find a discussion, decision, file reference, error, person, or topic | Lexical search, then show the cited sessions |
| Reconstruct when work happened or resume context | Cross-provider timeline, cited search, and bounded summary |
| Compare providers, models, roles, periods, or sessions | Matched search/analytics filters with explicit denominators |
| Diagnose retries, failed tools, escalations, or human intervention | analytics summary, tool-calls, escalations, hitl |
| Investigate instruction/control traffic or incident evidence | Control-event filters; forensic views only with explicit authorization |
| Find reusable requirements, decisions, risks, entities, relationships | session-harvest preview and candidate review |
| Explain imports, mutations, tombstones, or missing history | Coverage, doctor, and content-free audit; lifecycle recipe |
| Find expensive work | Correlate catalog evidence with cost-history; tool counts are not spend |
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- today First seen · 106 lines · 25 tokens per session scan A 31b3b51f29eb
session-explore is a skill published in the GitHub repository jmagly/aiwg (210 stars, last pushed yesterday), licensed MIT. It adds 25 tokens to every session and 1,180 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 2026-09-08.
Other skills, from other repositories
workflow-state-manager
Manages workflow state persistence and session recovery for sp.autonomous. Tracks phase progress, feature completion, and provides resume capability. Triggers: workflow state, session recovery, resume autonomous, progress tracking.
claudeception
Claudeception is a continuous learning system that extracts reusable knowledge from work sessions. Triggers: (1) /claudeception command to review session learnings, (2) "save this as a skill" or "extract a skill from this", (3) "what did we learn?", (4) After any task involving non-obvious debugging, workarounds, or…
report
Writes the session final report to a file, then prints only the path and a one-line summary. Fires when the prompt contains "Report per memstack:report", and also when the prompt begins with a standing trigger configured through MEMSTACKREPORTONTASKPROMPTS or MEMSTACKREPORTTRIGGERS. Dormant otherwise.
token-optimization
Use when the user says 'token optimization', 'save tokens', 'context window', 'reduce tokens', 'token stack', or 'TokenStack', or asks about extending context window capacity. Covers TokenStack, the built-in compression proxy that shrinks Claude Code tool output before it reaches the Anthropic API. Do NOT use for…
state
Use when the user says 'update state', 'project state', 'where was I', or at session start to load current context.
mulmoterminal-decisions
Check what this project's humans have already been asked, and how they answered, before asking them something similar. Reads MulmoTerminal's decision digest — the real questions from past sessions, the options each offered, and the answers they got, including the ones where the user rejected every option and wrote…