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/ain3sh/droid-session-explorer/dsxnpx skills add ain3sh/droid-session-explorer --skill dsxgit clone --depth 1 https://github.com/ain3sh/droid-session-explorerWrote 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/ain3sh/droid-session-explorer/dsx)<a href="https://agentmods.dev/skills/ain3sh/droid-session-explorer/dsx"><img src="https://agentmods.dev/badge/skills/ain3sh/droid-session-explorer/dsx.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 | $0.00052 | $0.01000 |
| Opus 5 | $0.00026 | $0.00500 |
| Sonnet 5 | $0.00010 | $0.00200 |
| Haiku 4.5 | $0.00005 | $0.00100 |
Grade A, and why
dsx 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 4d 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 — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
dsx: Droid Session Explorer
dsx indexes every local droid session (~/.factory/sessions) into a fast
SQLite+FTS5 index: full transcripts, token usage, tool calls, fork/subagent
lineage, and the user's prompt history. The index auto-refreshes before every
command (sub-second); add --no-refresh when running many commands in a row.
Every query command supports --json with stable shapes. Prefer it.
When this fires & how to load it
This entrypoint is enough for simple lookups. Load a reference when its trigger fires:
| Read | When |
|---|---|
references/commands.md |
composing non-trivial queries: full flag surface, FTS5 syntax, JSON hit shapes, export/maintenance commands |
references/usage-semantics.md |
reasoning about costs, tokens, fork inflation, subagents, or droid-exec exclusion |
references/stats-analytics.md |
reasoning about dsx stats cross-tabs, pro-rating, metrics, or distributions |
references/insights.md |
reasoning about dsx insights signal kinds, severity, and report-level rates |
Core workflow
Recovery trigger: after two failed attempts at the same operational or tooling problem, stop inventing new hypotheses and search history before a third. Query the exact error or distinctive symptom in the current project, then inspect the best prior session for the proven fix.
- Start broad:
dsx search "<query>" --jsonordsx list --jsonwith filters. - Drill in:
dsx show <id>for the shape,dsx export <id> --no-toolsfor content. - Cite session ids (8-char prefixes are fine) for every claim about past work.
- Costs and usage:
dsx stats --by model|project|day|day-model|day-project --since 30d. Before attributing cost, readreferences/usage-semantics.md(fork chains inherit cumulative usage; naive sums double-count). - "What went wrong lately":
dsx insights --since 30d. - Record small workflow friction in the moment with
dsx papercut add.
Quick reference
dsx list -q "auth refactor" --project vfs --since 7d --sort credits --json
dsx search "race condition" --type thinking --json # FTS5 over transcripts
dsx search "cache.*miss" --regex --json # ripgrep over raw JSONL
dsx search "refactor" --history --json # user's typed prompts
dsx show 22bc0eed --json # summary, usage, tool stats
dsx path 22bc0eed # JSONL= / SETTINGS= paths (add --all to scan disk for orphans)
dsx export 22bc0eed --no-tools # markdown transcript
dsx tree 22bc0eed # fork + subagent lineage
dsx resume 22bc0eed # prints the resume command
dsx stats --by model --since 30d --json
dsx stats --by day-model --metric totalTokens --since 30d --json
dsx stats --by day-tool --since 7d
dsx insights --since 30d --json # heuristic findings
dsx insights --deep # LLM-written usage brief
dsx ask "when did I last touch the auth flow?" # delegate to a sub-droid
dsx papercut add "The test cwd made the path miss." # durable manual record
dsx papercut list --project demo --json # query recorded friction
dsx papercut review 22bc0eed # preview transcript findings
dsx papercut review 22bc0eed --save # append reviewed findings
What ships with it
4 files 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.
- 4d ago First seen · 74 lines · 52 tokens per session scan A e41fd22b549c
dsx is a skill published in the GitHub repository ain3sh/droid-session-explorer (10 stars, last pushed yesterday), licensed MIT. It adds 52 tokens to every session and 1,000 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…