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-automationWrote 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-automation)<a href="https://agentmods.dev/skills/ashfulcra/fulcra-tools/fulcra-agent-automation"><img src="https://agentmods.dev/badge/skills/ashfulcra/fulcra-tools/fulcra-agent-automation/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-automation"><img src="https://agentmods.dev/badge/skills/ashfulcra/fulcra-tools/fulcra-agent-automation.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 | $0.00042 | $0.06019 |
| Opus 5.5 | $0.00017 | $0.02408 |
| Sonnet 5.5 | $0.00008 | $0.01204 |
| Haiku 4.5 | $0.00004 | $0.00602 |
Grade B, and why
fulcra-agent-automation scanned grade B with 1 finding 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
| Codex watch coord-first? | `grep -l "coord watch" ~/.codex/hooks.json` | file matches | §3 (install_codex_watch.py) | How it starts
The opening of the file, as written. The whole thing — 341 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Fulcra Agent Automation
BUS V3 (2026-07-27, operator-ordered): the listener half of this skill is RETIRED. Agents read their event queue on every wake — one bounded
get-recordsquery (docs/coord/BUS-V3.md) — and run no resident listener. Do not install new listeners (§2) or listener-tick automation; hosts still running one should stand it down. The heartbeat (§1: scheduledreconcile+ projection + digest) and the wake-on-schedule adapters (§3, repurposed to trigger a queue-reading wake rather than a listen tick) remain current. Thelistenverb itself was REMOVED from the engine on 2026-08-03 (PR #523); invoking it is now an argparse error.
Ties the coord skills together for unattended operation. fulcra-agent-reconcile heals a team's
index/views, but someone has to run it; this skill schedules it, and makes wake-ups
(cron/heartbeat) resume structured continuity first. Scheduling is a single, platform-specific action
(not a fold), so this skill is prose + one bundled install script — no engine logic.
Require consent: always ask the user before creating any scheduled job or background automation.
Where to start — the re-entrancy probes
Before installing anything, probe what this host already runs. Enter at the first probe that
fails (per the repo's skill-quality pattern, docs/skill-quality-pattern.md):
| Probe (run in order) | Command | Passes when | If it fails, enter at |
|---|---|---|---|
| Engine usable? | coord-engine doctor <team> |
exits 0 and last line is doctor: healthy |
fix engine/auth first (see fulcra-agent-reconcile) — do NOT install jobs on a broken engine |
| Heartbeat installed? | ls ~/Library/LaunchAgents/com.fulcra.coord-engine.heartbeat.<team>.plist (macOS) or crontab -l | grep coord-engine.heartbeat.<team> (Linux) |
file/line exists | §1 (install the heartbeat) |
| Heartbeat loaded? | launchctl list | grep coord-engine.heartbeat.<team> (macOS only) |
a line appears | reinstall via §1 (plist exists but is not loaded — a reboot-era failure mode) |
| Listener installed + loaded? (RETIRED — see banner) | ls ~/Library/LaunchAgents/com.fulcra.coord-engine.listener.<team>.*.plist and launchctl list | grep coord-engine.listener.<team>. |
inverted since bus v3: this probe passing means a retired listener is still running — stand it down: launchctl bootout gui/$(id -u)/<label> && rm ~/Library/LaunchAgents/<label>.plist (macOS) or delete its crontab line (Linux); the installer script was removed with the listener stack |
nothing — a missing listener is now the healthy state; do NOT enter §2 |
| Views actually fresh? | coord-engine health <team> |
this host's row shows a recent last reconcile |
jobs exist but are not ticking — check log show / cron mail, then reinstall |
| Claude Code hooks installed? | ls ~/.claude/fulcra-agent-hooks/ |
3 scripts | §3 (install-claude-code.sh) |
| Codex watch coord-first? | grep -l "coord watch" ~/.codex/hooks.json |
file matches | §3 (install_codex_watch.py) |
| OpenClaw block present? | grep "fulcra-agent:begin" <workspace>/HEARTBEAT.md |
one match | §3 (install_openclaw.py) |
What ships with it
8 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.
- scripts/claude-code/install-claude-code.sh 5.0 KB runs code
- scripts/claude-code/pre-compact.sh 560 B runs code
- scripts/claude-code/session-end.sh 560 B runs code
- scripts/claude-code/session-start.sh 1.4 KB runs code
- scripts/codex/install_codex_watch.py 23 KB runs code
- scripts/install-heartbeat.sh 8.1 KB runs code
- scripts/openclaw/install_openclaw.py 16 KB runs code
- scripts/wake/macos-notify.sh 3.4 KB runs code
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 2061d77dfe52
- 1mo ago First seen · 341 lines · 42 tokens per session scan B 2217ea763233
fulcra-agent-automation is a skill published in the GitHub repository ashfulcra/fulcra-tools (10 stars, last pushed 8d ago), licensed MIT. It adds 42 tokens to every session and 6,019 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it B with 1 finding (reads agent configuration directories). 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.
citation-intelligence
Use when the user wants to know which URLs AI engines cite for a query, whether their domain is being cited by ChatGPT/Claude/Perplexity/Gemini/Google AI Overviews/Bing, what queries their site is cited for, how citation rate changes over time, or how their citation coverage compares to competitors. Self-hosted, BYO…
proof-engine
Create formal, verifiable proofs of claims with machine-checkable reasoning. Use when asked to prove, verify, fact-check, or rigorously establish whether a claim is true or false — mathematical, empirical, or mixed. Trigger phrases: "is it really true", "can you prove", "verify this", "fact-check this", "prove it"…
analytics
Social media analytics for the Ayrshare MCP server — metrics for a specific post, and account/network-level analytics on a connected social network (followers, impressions, reach, demographics). Use whenever someone wants performance data: "how did my post do", "engagement on that tweet"…
messages
Direct messages (DMs) for the Ayrshare MCP server: read conversations and messages, send a DM, and manage the account's DM auto-responder. Use whenever someone wants private/direct messages on Facebook, Instagram, or Twitter/X: "read my Instagram DMs", "show our Facebook conversations", "what messages came in on X"…
plan-and-schedule-campaign
Plan a multi-post, multi-platform social campaign and schedule it across networks via the Ayrshare MCP server: adapt copy and timing per platform, validate each post before it is scheduled, and confirm with the user before anything goes live. Use whenever someone wants more than one scheduled post: "plan a content…