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 gyoung55/cowork-session-skills --skill concludegit clone --depth 1 https://github.com/gyoung55/cowork-session-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/gyoung55/cowork-session-skills/conclude)<a href="https://agentmods.dev/skills/gyoung55/cowork-session-skills/conclude"><img src="https://agentmods.dev/badge/skills/gyoung55/cowork-session-skills/conclude/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/gyoung55/cowork-session-skills/conclude"><img src="https://agentmods.dev/badge/skills/gyoung55/cowork-session-skills/conclude.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 | $0.00078 | $0.02073 |
| Opus 5 | $0.00039 | $0.01037 |
| Sonnet 5 | $0.00016 | $0.00415 |
| Haiku 4.5 | $0.00008 | $0.00207 |
Grade A, and why
conclude 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 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.
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 — 197 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Session Conclude
This skill closes out a session completely. It captures everything that happened — progress, decisions, context discussed, files modified, open threads — so that any new session can pick up exactly where this one left off with zero reconstruction.
Every session must produce a session log. This is non-negotiable. When the user signals the session is ending, execute this protocol in full.
Why This Exists
Work on persistent projects is scattered across sessions, tools, and time. The session log is the connective tissue. Without it, the next session starts cold and context gets lost. The /standup skill ingests what this skill produces. They are a matched pair.
Execution Steps
Run these steps sequentially. Do not skip steps. Confirm the output with the user at the end.
Step 1: Session Audit
Before writing anything, systematically scan the full conversation to build a complete picture of what happened. This is the most important step — a thorough audit prevents the log from missing things.
Identify and list:
- Every file created this session (full path)
- Every file modified this session (full path + one-line summary of what changed)
- Every file moved or deleted this session
- Every decision made (with rationale — why, not just what)
- Every open thread — anything unfinished, questions raised but not answered, next actions identified
- Every piece of context the user provided that isn't captured in existing docs (corrections, reframing, new information, things future sessions need to know)
- Cross-project implications — did anything this session produce findings relevant to other projects?
- Session type classification — what category best describes the primary focus of this session
Take your time on this step. Scan the full conversation, not just recent messages. Long sessions are where things get missed.
Step 2: Write Session Log
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 · 197 lines · 78 tokens per session scan A aa58cc36de0e
conclude is a skill published in the GitHub repository gyoung55/cowork-session-skills (5 stars, last pushed 5mo ago), licensed MIT. It adds 78 tokens to every session and 2,073 once invoked, about $0.0004 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 2026-08-30.
Other skills, from other repositories
media-ingest
Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain. Multi-format handling with entity extraction and backlink propagation. Covers video-ingest, youtube-ingest, and book-ingest subtypes.
mem0-oss-to-platform
Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
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…
establishing-project-context
Use when the user asks to establish shared project language, or project work exposes a conflicting, renamed, or deprecated domain term that needs active semantic modeling. Routine small tasks stay on the fast path.