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 Openly-Useful/project-status --skill runglancegit clone --depth 1 https://github.com/Openly-Useful/project-statusWrote 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/openly-useful/project-status/runglance)<a href="https://agentmods.dev/skills/openly-useful/project-status/runglance"><img src="https://agentmods.dev/badge/skills/openly-useful/project-status/runglance.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 5.1 | $0.00099 | $0.01353 |
| Opus 5 | $0.00049 | $0.00677 |
| Sonnet 5 | $0.00020 | $0.00271 |
| Haiku 4.5 | $0.00010 | $0.00135 |
Grade A, and why
runglance 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 today.
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 — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.
StatusGlance / RunGlance
Give users an immediate, evidence-honest answer to “what is running, is it stuck, and what finished?” Keep the terminal HUD local and dependency-free; use the MCP companion only when a model needs bounded status queries.
Default invocation: one read-only snapshot
Calling $runglance means inspect existing activity once. Use the known task session and runtime, or one bounded MCP query. Do not start a run, install hooks, watch, run tests, update the ledger, or emit a finish receipt merely to answer status. If no telemetry exists, report not connected / no events observed; do not manufacture activity.
node <skill-dir>/scripts/runglance.mjs show --session-id <known-session> --preset swarm
An explicit session or isolated runtime prevents cross-project selection. Multiple sessions without a selection are ambiguous. Show each lane's latest concrete result, blocker/next action, and measured progress when its denominator exists; otherwise show unknown. Distinguish implemented, tested, and accepted. Report repeated revision or stale evidence without launching corrective work from a status-only request.
During authorized execution, record meaningful lifecycle/progress deltas and milestone verification, not every message or refresh. Reuse host events and existing task IDs. Use one local deterministic HUD process only when live watching was requested; do not schedule model polling. Loop roles are responsibilities, not mandatory extra agents.
Preserve the truth boundary
- Report host-provided facts as
exact, calculated facts asderived, opt-in approximations asestimated, and unavailable facts asunknown. - Never convert token counts into subscription quota, invent context capacity, or treat silence as a lock.
- Report
lockedonly after an explicit lock event with an owner. A missed heartbeat can reportstale. - Keep run progress separate from project readiness. A passing check proves only that check.
- Do not persist prompts, responses, transcripts, environment variables, credentials, raw tool arguments, or source files.
What ships with it
7 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.
- today Changed · +14 lines b00a18265750
- 8d ago First seen · 80 lines · 99 tokens per session scan A 73bbebe0f5a9
runglance is a skill published in the GitHub repository Openly-Useful/project-status (0 stars, last pushed today), licensed Apache-2.0. It adds 99 tokens to every session and 1,353 once invoked, about $0.0005 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 2026-08-31.
Other skills, from other repositories
hevy-cli
Manage Hevy workouts from the terminal: read and summarize training data, search exercise templates, and create or update workouts, routines, exercises, folders, or body measurements.
help-flow
Help about Rosetta: explains capabilities and usage.
external-lib-flow
Workflow for onboarding an external private library so AI can use it without source access.
memora
Use when working with persistent memory across sessions, storing/retrieving knowledge, managing TODOs/issues, or when context from previous sessions would be helpful.
coding-flow
Light coding workflow: features, fixes, refactors, unit tests, etc.; scales small to large.
coding-agents-prompting-flow
Workflow for authoring and adapting AI-agent prompts: skills, agents, workflows, rules, etc.