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/mishahanin/heading-osnpx agentmods add skills/mishahanin/heading-os/bridge-healthWrote 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/mishahanin/heading-os/bridge-health)<a href="https://agentmods.dev/skills/mishahanin/heading-os/bridge-health"><img src="https://agentmods.dev/badge/skills/mishahanin/heading-os/bridge-health/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/mishahanin/heading-os/bridge-health"><img src="https://agentmods.dev/badge/skills/mishahanin/heading-os/bridge-health.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 | $0.00086 | $0.02089 |
| Opus 5 | $0.00043 | $0.01045 |
| Sonnet 5 | $0.00017 | $0.00418 |
| Haiku 4.5 | $0.00009 | $0.00209 |
Grade B, and why
bridge-health scanned grade B with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Sends data to an external URLmediumData exfiltration
A POST to an outside endpoint may be telemetry or may be exfiltration; either way the mod talks to somewhere, and you should know where.
`curl -sS -X POST "http://127.0.0.1:$PORT/refresh" -H "Authorization: Bearer $TOKEN" -H 'Content-Type: application/json' -d '{"component":"pulse"}'`. Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
`curl -sS -X POST "http://127.0.0.1:$PORT/refresh" -H "Authorization: Bearer $TOKEN" -H 'Content-Type: application/json' -d '{"component":"pulse"}'`. How it starts
The opening of the file, as written. The whole thing — 170 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Bridge daemon health check
Wraps two CLI scripts into a single CEO ops command:
scripts/daemon-fleet-health.py-- fleet status grid (heartbeat freshness, version drift, active session count per workspace)scripts/bridge-daemon.py --health-- live/healthendpoint probe on the local daemon
Optionally surfaces the adoption-gate metrics (Phase 1 -> Phase 2 gate from
the bridge spec, section 4) when called with --gate.
When to use
- Sync-pill on the dashboard is amber or red
- /push-updates pushed a daemon config change and the CEO wants to verify the fleet picked it up
- The dashboard feels stale and you don't know if the daemon is dead or just slow
- Before deciding whether to scale: Phase 1 (CEO only) to Phase 2 (full CEO
coverage), or Phase 3 (exec pilot).
--gateshows the gate verdict
When NOT to use
- Single-script debugging: prefer
python scripts/bridge-daemon.py --healthdirectly when the question is "is this daemon process alive on this machine right now". /bridge-health is for the rollup. - One-line grep summary: prefer
python scripts/bridge-daemon.py --statusfor a single grep-friendly line (port + pid + uptime + version + config_v + sessions + errors + last_hb). Designed for cron + shell pipelines. - Triggering refresh: there is no
--refreshCLI flag. The terminal path is a POST to the loopback endpoint. Read the port and bearer token from.daemon-state/portand.daemon-state/token, the way step 3 below reads them for/telemetry/summary. Then run:curl -sS -X POST "http://127.0.0.1:$PORT/refresh" -H "Authorization: Bearer $TOKEN" -H 'Content-Type: application/json' -d '{"component":"pulse"}'. The dashboard's sync-pill calls that same endpoint. It is a convenience, not the only way in. The daemon also refreshes on its own interval, so force a refresh only to get one early. - Tweaking config: edit
corporate/daemon/config.yaml, commit, run /push-updates. /bridge-health is read-only.
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 Changed · +7 lines scan A → B 88b9eee664d2
- 12d ago First seen · 163 lines · 86 tokens per session scan A 63e8ce3b1f17
bridge-health is a skill published in the GitHub repository mishahanin/heading-os (11 stars, last pushed 3d ago), licensed Apache-2.0. It adds 86 tokens to every session and 2,089 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it B with 2 findings (sends data to an external url, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
terraform-expert
Expert-level Terraform infrastructure as code, modules, state management, and production best practices. Use when the user mentions infrastructure as code, devops, or automation, or when the task involves Terraform Basics, Resource Management, Modules, or State Management.
modal
Serverless GPU cloud for ML jobs and model APIs.
cloudflare-temporary-deploy
Deploy a Worker live, no account, via wrangler --temporary.
tensorrt-llm
High-throughput LLM inference on NVIDIA GPUs.
stripe-projects
Provision SaaS services + sync creds via Stripe Projects.
environments
How Open SWE environments work and how to change them — create one, edit or fork an existing one, start from scratch, what setupscript and updatescript are for, why a nightly refresh failed, where the build logs are, and how to read a rebuild in progress. Read this whenever someone asks about environments, snapshots…