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/openclaw/agent-skills/session-viewernpx skills add openclaw/agent-skills --skill session-viewergit clone --depth 1 https://github.com/openclaw/agent-skillsWrote 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/openclaw/agent-skills/session-viewer)<a href="https://agentmods.dev/skills/openclaw/agent-skills/session-viewer"><img src="https://agentmods.dev/badge/skills/openclaw/agent-skills/session-viewer.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 | $0.00032 | $0.00786 |
| Opus 5 | $0.00016 | $0.00393 |
| Sonnet 5 | $0.00006 | $0.00157 |
| Haiku 4.5 | $0.00003 | $0.00079 |
Grade B, and why
session-viewer scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
find "$HOME/.claude/projects" -name '*.jsonl' -type f | sort How it starts
The opening of the file, as written. The whole thing — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Session Viewer
Use when asked to view, export, inspect, or share a Codex, Claude Code, OpenClaw, or Pi session transcript in a browser.
Commands
When the session path is not known and the agent-transcript skill is available, use it first to find the likely JSONL session:
.agents/skills/agent-transcript/scripts/agent-transcript find \
--query "$USER_GOAL_OR_TITLE $BRANCH_OR_URL" \
--cwd "$PWD" \
--since-days 14
Pick the highest-confidence file result, then render it with session-viewer.
From a repo that has this skill:
node skills/session-viewer/scripts/session-viewer.ts <session.jsonl> --out /tmp/session.html --open
Useful modes:
node skills/session-viewer/scripts/session-viewer.ts <session.jsonl> --out session.html
node skills/session-viewer/scripts/session-viewer.ts <session.jsonl> --raw --out session.html
node skills/session-viewer/scripts/session-viewer.ts --blank --out viewer.html --open
In a downstream repo that syncs shared skills under .agents/skills, replace
skills/session-viewer with .agents/skills/session-viewer.
Defaults:
- detects
codex,claude, orpi-openclaw - embeds normalized session data into one HTML file
- keeps tool input/output text in the DOM so browser search can find it
--rawembeds the original JSONL and lets the browser parse it--blankcreates a reusable file-picker viewer
Where Sessions Live
Codex:
find "${CODEX_HOME:-$HOME/.codex}/sessions" -name 'rollout-*.jsonl' -type f | sort
ls -t "${CODEX_HOME:-$HOME/.codex}"/sessions/*/*/*/rollout-*.jsonl | head
OpenClaw/Pi:
AGENT_ID="<agentId>"
SESSION_DIR="${OPENCLAW_STATE_DIR:-$HOME/.openclaw}/agents/$AGENT_ID/sessions"
ls -t "$SESSION_DIR"/*.jsonl | head
find "${OPENCLAW_STATE_DIR:-$HOME/.openclaw}/agents" -path '*/sessions/*.jsonl' -type f | sort
Use sessions.json in the same directory to map session keys to session ids.
Claude Code:
find "$HOME/.claude/projects" -name '*.jsonl' -type f | sort
ls -t "$HOME/.claude/projects"/**/*.jsonl | head
What ships with it
12 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.
- agents/openai.yaml 207 B
- scripts/core/detect.ts 1.0 KB runs code
- scripts/core/jsonl.ts 7.5 KB runs code
- scripts/core/types.ts 1.0 KB runs code
- scripts/html.ts 49 KB runs code
- scripts/importers/claude.ts 5.6 KB runs code
- scripts/importers/codex.ts 8.0 KB runs code
- scripts/importers/pi-openclaw.ts 7.9 KB runs code
- scripts/open-browser.ts 435 B runs code
- scripts/session-viewer.test.ts 23 KB runs code
- scripts/session-viewer.ts 3.9 KB runs code
- tsconfig.json 276 B
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 · 98 lines · 32 tokens per session scan B 89b6f03e0fe0
session-viewer is a skill published in the GitHub repository openclaw/agent-skills (1,070 stars, last pushed 4d ago), licensed MIT. It adds 32 tokens to every session and 786 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
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…