Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/ashfulcra/fulcra-toolsnpx agentmods add skills/ashfulcra/fulcra-tools/fulcra-agent-continuityWrote 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/ashfulcra/fulcra-tools/fulcra-agent-continuity)<a href="https://agentmods.dev/skills/ashfulcra/fulcra-tools/fulcra-agent-continuity"><img src="https://agentmods.dev/badge/skills/ashfulcra/fulcra-tools/fulcra-agent-continuity/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/ashfulcra/fulcra-tools/fulcra-agent-continuity"><img src="https://agentmods.dev/badge/skills/ashfulcra/fulcra-tools/fulcra-agent-continuity.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00054 | $0.03876 |
| Opus 5.5 | $0.00022 | $0.01550 |
| Sonnet 5.5 | $0.00011 | $0.00775 |
| Haiku 4.5 | $0.00005 | $0.00388 |
Grade A, and why
fulcra-agent-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 1mo 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 — 243 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Fulcra Agent Continuity
Enhances the fulcra-agent-teams skill. Teams already
uses member/<agent>/progress.md to survive isolated cron/heartbeat runs, but it's freeform — a fresh
session has to re-read prose and guess what mattered. This skill adds a structured snapshot
(objective, decisions, next actions, open questions, artifacts, context-used-%) and a deterministic
resume brief, so waking up is reliable instead of a re-read.
Whether/when to snapshot is a judgment call (prose); building the schema and folding many snapshots to
the newest is deterministic (the coord-engine tool).
The lifecycle contract (applies on every harness)
Any agent participating in a team space owes these four behaviors. Harness adapters (see fulcra-agent-automation §Harness adapters) automate them where the platform allows; where it doesn't, follow them as prose:
- On wake (new session, cron fire, heartbeat, automation tick):
coord-engine continuity resume <team> <agent>and read your inbox (coord-engine inbox <team> --agent <agent>) BEFORE taking new work. - On material change (a decision made, an artifact produced, a task claimed or
finished) and at least hourly while actively working:
coord-engine continuity snapshot <team> <agent> <task> --objective … [--decision …] [--next …]. - Before context loss (compaction, model handoff, session end):
coord-engine continuity park <team> --agent <agent> --objective "<one line>"— parks every held role with a checkpoint. Handing off to a successor session? The checkpoint's CONTENT has rules of its own — see Parking for a successor. - Inbox cadence: while live, read your queue and inbox at least every 30 minutes. If your
platform has a durable scheduler, arm ONE scheduled wake that runs
coord-engine queue <team> --agent <you>instead of trusting yourself — a schedule, never a resident listener (those are retired; see the pickup note below).
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.
- 1mo ago Changed · -1 lines f8e707f4acff
- 1mo ago First seen · 244 lines · 54 tokens per session scan A 5f2d65b861bc
fulcra-agent-continuity is a skill published in the GitHub repository ashfulcra/fulcra-tools (10 stars, last pushed 8d ago), licensed MIT. It adds 54 tokens to every session and 3,876 once invoked, about $0.0002 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
magic-compact
Compact this Claude Code session.
mem0-vercel-ai-sdk
Mem0 provider for Vercel AI SDK (@mem0/vercel-ai-provider). TRIGGER when: user mentions "vercel ai sdk", "@mem0/vercel-ai-provider", "createMem0", "retrieveMemories", "addMemories", "getMemories", "searchMemories", "mem0 vercel", "AI SDK provider", "AI SDK memory", or is using generateText/streamText with mem0. Also…
mem0-tour
Browses all stored memories grouped by category with full content display. Use when reviewing all project memories, exploring stored knowledge, onboarding to a project, or getting an overview of captured decisions, conventions, and learnings.
pause
Pause Mem0 memory capture on this machine. Use when the user wants to stop memories being recorded, for example for private work or experiments.
agent-carnet
Use this skill when the user asks to save, recall, find, or organize notes. Triggers on: 'remember this', 'save this', 'note this', 'what did we discuss about...', 'check the notebook', 'find in carnet'. Also use proactively when discovering findings worth preserving across sessions.
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…