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 shaharsha/claude-skills --skill working-with-other-sessionsgit clone --depth 1 https://github.com/shaharsha/claude-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/shaharsha/claude-skills/working-with-other-sessions)<a href="https://agentmods.dev/skills/shaharsha/claude-skills/working-with-other-sessions"><img src="https://agentmods.dev/badge/skills/shaharsha/claude-skills/working-with-other-sessions/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/shaharsha/claude-skills/working-with-other-sessions"><img src="https://agentmods.dev/badge/skills/shaharsha/claude-skills/working-with-other-sessions.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 | $0.00167 | $0.09496 |
| Opus 5 | $0.00084 | $0.04748 |
| Sonnet 5 | $0.00033 | $0.01899 |
| Haiku 4.5 | $0.00017 | $0.00950 |
Grade B, and why
working-with-other-sessions 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 12d 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 ~/.claude/projects -name '<that uuid>*.jsonl' -> 0 files, for three such entries How it starts
The opening of the file, as written. The whole thing — 487 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Working with other sessions
Core principle
A session's reasoning survives only in its prose. The diff shows what changed; the PR shows the pitch; the ticket shows the plan. What the session found, what it refuted, what it flagged about its own work, and what it decided not to do exist nowhere but the transcript.
A transcript is ~95% tool calls and tool results. Reading it with cat, grep or jq buries the conversation under machine noise — which is why the interesting parts get missed.
When to use
- Several sessions run in parallel and you need to know what each is doing, or whether two have collided
- A PR, branch or commit appeared and you need its owner
- A session is idle and you need to know whether it is blocked on a question
- A session disappeared from the session list
- You suspect work was already done, or already refuted, somewhere else
- You are about to repeat an investigation another session may have finished
Not for: reading your own current conversation, or grepping code. Use ordinary tools for those.
Quick reference
Three scripts, no install: scripts/ccread (read), scripts/ccsend (send), scripts/ccarm (receive).
⚠️ Renaming this skill breaks every session already running. A live session holds the absolute
path it first resolved — ~/.claude/skills/<old-name>/scripts/ccsend — in its own context, and no
amount of re-reading the skill dislodges it. Measured 2026-08-07: the rename to
working-with-other-sessions turned that path into exit 127 for 46 sessions mid-sprint,
including the sprint's own coordinator, whose outbound channel simply stopped working with no error
anyone saw until a lane was asked why it had gone quiet. Leave a scripts/-only symlink at the old
name — no SKILL.md, since skill discovery keys on that file and a full-directory symlink registers
the skill twice under both names.
| Need | Command |
|---|---|
| What's running, and what's stale | ccread |
| Which lane is which (every title goes stale) | ccread --doing |
| Only recent | ccread --since 2026-07-29 |
| Read one session's conversation | ccread "TOR-55" |
| What is it doing right now | ccread <id> --last 20 |
| Only since this morning | ccread <id> --from 06:00 |
| With tool calls interleaved | ccread <id> --tools |
| Find a topic in one session | ccread <id> --grep codex |
| Find a topic across all sessions | ccread --all --grep "credential" --since 2026-07-29 |
What ships with it
8 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.
- 12d ago First seen · 487 lines · 167 tokens per session scan B 5822796b6351
working-with-other-sessions is a skill published in the GitHub repository shaharsha/claude-skills (5 stars, last pushed 14d ago), licensed MIT. It adds 167 tokens to every session and 9,496 once invoked, about $0.0008 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
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…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…