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/escapeboy/ai-prompts/continuitynpx skills add escapeboy/ai-prompts --skill continuitygit clone --depth 1 https://github.com/escapeboy/ai-promptsWrote 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/escapeboy/ai-prompts/continuity)<a href="https://agentmods.dev/skills/escapeboy/ai-prompts/continuity"><img src="https://agentmods.dev/badge/skills/escapeboy/ai-prompts/continuity.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 | $0.00125 | $0.01326 |
| Opus 5 | $0.00063 | $0.00663 |
| Sonnet 5 | $0.00025 | $0.00265 |
| Haiku 4.5 | $0.00013 | $0.00133 |
Grade A, and why
continuity 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 5d 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 — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Continuity — resume → work → finalize
The bottleneck between coding sessions is not memory volume, it is the lost operational thread: what is mid-flight, what already failed, what to do next. Big context, vector recall, and chat history all "remember more" yet still miss the one fact that matters (this command already failed). This skill keeps that thread in a small repo-local artifact and runs a lifecycle over it.
Core loop: resume (bounded start surface) → work → finalize (leave evidence).
Without the lifecycle, memory is passive archaeology. With it, memory becomes execution.
When to Use This Skill (and When NOT to)
| Use this skill for | Use a simpler approach for |
|---|---|
| Multi-session work on one repo (feature, refactor, migration) | A one-shot question or single-file edit — just answer |
| Picking up work where re-orientation would otherwise eat the first 10 min | A repo you'll touch once and never return to |
| Recording why a decision/dead-end happened so it isn't repeated | Facts already better held elsewhere (arch → Serena, cross-project → Harbormaster, durable policy → Svod) |
| Handing a repo to another agent or teammate | Ephemeral session chatter — let auto-memory handle it |
Start simple. Reach for this skill only when the work spans more than one session
on the same repo. Do NOT create a .continuity/ for throwaway or single-shot tasks —
that is the sixth-memory-store trap this skill is explicitly built to avoid.
The artifact
Repo-local .continuity/ (scaffold with the script below):
.continuity/STATE.md— the bounded resume surface AND the finalize target (one living, compacted doc — not an append-only journal). Portable → committable/shareable..continuity/local/— gitignored, machine-specific operational scratch. Local-only.
Every fact carries an evidence tag (weight, not decoration):
[observed] [validated] [user] — trust · [claimed] [contradicted] [unknown] — low trust.
Full section spec, tag semantics, and a worked example: references/format.md.
What ships with it
2 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.
- 5d ago First seen · 99 lines · 125 tokens per session scan A a84656257ff2
continuity is a skill published in the GitHub repository escapeboy/ai-prompts (91 stars, last pushed 9d ago), licensed MIT. It adds 125 tokens to every session and 1,326 once invoked, about $0.0006 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
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.
release
Cut a versioned release and publish everos to PyPI via the tag-triggered workflow.
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…
Daemon
Manage the public daemon profile — a digital representation of what you're working on. DaemonAggregator reads LifeOS sources (TELOS, KNOWLEDGE, PROJECTS, MEMORY/WORK, identity) → daemon-data.json. SecurityFilter strips names/paths/credentials via deterministic patterns (NOT LLM). Workflows: UpdateDaemon, ReadDaemon…
Migrate
Intakes external content, classifies chunks against LifeOS taxonomy, commits with provenance. Sources: .md/.txt, stdin, LifeOS dirs, CLAUDE.md/Cursor/OpenAI Custom Instructions, Obsidian/Notion/Apple Notes exports. MigrateScan classifies → routing table. MigrateApprove with…
personal-assistant
A personalized assistant that remembers your preferences.