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 LiozShor/claude-code-skills --skill find-sessiongit clone --depth 1 https://github.com/LiozShor/claude-code-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/liozshor/claude-code-skills/find-session)<a href="https://agentmods.dev/skills/liozshor/claude-code-skills/find-session"><img src="https://agentmods.dev/badge/skills/liozshor/claude-code-skills/find-session/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/liozshor/claude-code-skills/find-session"><img src="https://agentmods.dev/badge/skills/liozshor/claude-code-skills/find-session.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 | $0.00036 | $0.01782 |
| Opus 5.5 | $0.00014 | $0.00713 |
| Sonnet 5.5 | $0.00007 | $0.00356 |
| Haiku 4.5 | $0.00004 | $0.00178 |
Grade A, and why
find-session 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 2mo 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 — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Find Session
Search Claude Code's local session logs (~/.claude/projects/**/*.jsonl) for a past conversation matching the user's description, and return resume instructions (or, when the user really wants an artifact the session produced, hand them that file directly).
When this triggers
- "I closed / accidentally quit my session, help me find it."
- "Which session did we discuss / fix / build X in?"
- "Find the session where we worked on DL-142 / the upload bug / the nav redesign."
- "Where did the two project agents talk to each other?" (cross-project conversations count).
- Any request to locate a past Claude Code conversation by topic, error text, file, or feature so it can be resumed or referenced.
When this does not trigger
- The user wants the contents of a file a session wrote, and the session itself is irrelevant → just
Readthe file; don't hunt sessions. - The user wants git history, commits, or PRs → use
git log, not session logs. - The user is asking about the current live session or its context → that's not a search.
- The user wants to resume a specific known session id → they can
claude --resume <id>directly; only help translate the worktree path.
Required inputs
- A search hint: a distinctive phrase, error message, feature name, DL number, file path, or topic. Shorter and more distinctive beats vague ("preview load failed", "DL-142 react port", an agent or feature name > "that bug we fixed").
- If no hint is given, ask for one before searching. If the user only has a rough time ("this morning", "just now"), that alone is enough to rank by mtime — proceed.
Where sessions live
- One project dir per
cwdunder~/.claude/projects/, named by the slugified path (/→-). - Worktrees are separate project dirs — a freshly-closed session often lives in a
...-worktrees-...-claude-<repo>-YYYYMMDD-HHMMSSdir, NOT the main repo dir. Always include them. - Cross-project topics span sibling dirs. A conversation between two agents/projects has two session files in two different project dirs — search siblings and expect both ends to be relevant.
- Each
.jsonlfile is one session. Filename (minus extension) is the session id. File mtime ≈ last active time.
What ships with it
3 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.
- 2mo ago First seen · 116 lines · 36 tokens per session scan A 410a748f127f
find-session is a skill published in the GitHub repository LiozShor/claude-code-skills (2 stars, last pushed 2mo ago), licensed MIT. It adds 36 tokens to every session and 1,782 once invoked, about $0.0001 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 2026-08-31.
Other skills, from other repositories
knowledge-ingest
Ingest documents, articles, conversations, or supplied text into Knowledge with retained originals, sourced claims, entity updates, source notes, and cross-links; also learn durable lessons from a set of conversations, transcripts, or past sessions (/learn), including the Learn from conversations and Learn from Memory…
forget
Remove a personal fact, preference, relationship detail, topic, or prior event from Muse's active memory and stop existing copies or automations from bringing it back. Use for explicit requests such as 'forget that', 'don't remember this about me', or 'remove that from your memory'. Do not use when 'forget it' merely…
mem0-oss-to-platform
Plan, then execute, a migration of a project from the mem0 open-source / self-hosted SDK (local Memory class) to the mem0 Platform / hosted SDK (MemoryClient). TRIGGER when: the developer wants to move, switch, or migrate mem0 off OSS/self-hosted to the hosted API, e.g. "migrate my mem0 setup to the platform", "switch…
Cortex
LifeOS memory, prior-session recall, and learning capture. USE WHEN capture this learning, document this learning, what did we learn recently, recent learnings, cortex, knowledge, knowledge base, search knowledge, what do we know about, archive, harvest, knowledge status, develop note, add to knowledge, add a people…
memory
Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.
ha-data-stores
Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…