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 digital-stoic-org/agent-skills --skill save-workgit clone --depth 1 https://github.com/digital-stoic-org/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/digital-stoic-org/agent-skills/save-work)<a href="https://agentmods.dev/skills/digital-stoic-org/agent-skills/save-work"><img src="https://agentmods.dev/badge/skills/digital-stoic-org/agent-skills/save-work.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 5 Skill selects an external model or provider that may use a different account or billing plan than the operator expects. Undisclosed model switches can cause unexpected cost or quota consumption.Fix: Remove the model/provider override or disclose it prominently and require explicit operator approval before invoking an external coding CLI or billed model.
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 | $0.00035 | $0.01663 |
| Opus 5 | $0.00017 | $0.00831 |
| Sonnet 5 | $0.00007 | $0.00333 |
| Haiku 4.5 | $0.00003 | $0.00166 |
Grade A, and why
save-work 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 8d 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 — 165 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Save Session
Menu-driven session save for non-CLI interfaces (Cowork desktop, Telegram, CC CLI).
Same CONTEXT file format as retrospect:save-context / retrospect:load-context — files are interchangeable.
Target: 1200-1500 tokens MAX for CONTEXT file
Phase 1: Detect Current Project (parallel)
Glob: CONTEXT-*-llm.md (current dir, exclude done/)
Read: CLAUDE.md (first 5 lines, for project name from H1 — required)
Identify:
- Project name (from CLAUDE.md H1 heading — all CLAUDE.md files must have
# Project Nameas first line) - Existing CONTEXT streams (filenames → stream names)
If no CLAUDE.md found in current dir or parents → warn: "⚠️ No project context detected. Use /switch first to select a project."
Before Phase 2: run quality self-check from reference.md — if session is trivial, confirm with user before proceeding.
⚠️ AskUserQuestion Guard
After EVERY AskUserQuestion call, check if answers are empty/blank. If empty: output "⚠️ Questions didn't display (known bug).", present options as numbered text list, WAIT for user reply.
Phase 2: Ask Save Type + Stream (single menu when possible)
0-1 existing streams → merge type + stream into 1 question:
💾 Save {stream-name} as:
1. 🔄 Checkpoint — I'll continue later
2. ✅ Done — this work is finished
3. 🅿️ Parking — switching to something else
Which one? (1/2/3)
Where {stream-name} = existing stream name, or auto-generated from project + conversation topic if no streams exist.
2+ existing streams → 2 questions. First ask stream:
📝 Save to which session?
1. 📍 {stream-1} (existing)
2. 📍 {stream-2} (existing)
3. ✨ New session
Which one?
Then ask save type (same 3-choice menu as above).
New stream confirmation (when auto-generated or user picks "New"):
📝 Stream name: {suggested-name}
OK? (yes / type a different name)
Mapping:
- 1 → status:
building - 2 → status:
done - 3 → status:
parked
Stream naming: pattern ^[a-zA-Z0-9_-]{1,50}$. Reserved: default → CONTEXT-llm.md, baseline.
What ships with it
1 file 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.
- 8d ago First seen · 165 lines · 35 tokens per session scan A 42d7ccac5e97
save-work is a skill published in the GitHub repository digital-stoic-org/agent-skills (20 stars, last pushed yesterday), licensed MIT. It adds 35 tokens to every session and 1,663 once invoked, about $0.0002 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.