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/leopu00/job-hunter-teamnpx agentmods add skills/leopu00/job-hunter-team/agent-emergencyWrote 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/leopu00/job-hunter-team/agent-emergency)<a href="https://agentmods.dev/skills/leopu00/job-hunter-team/agent-emergency"><img src="https://agentmods.dev/badge/skills/leopu00/job-hunter-team/agent-emergency/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/leopu00/job-hunter-team/agent-emergency"><img src="https://agentmods.dev/badge/skills/leopu00/job-hunter-team/agent-emergency.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 | $0.00000 | $0.01783 |
| Opus 5 | $0.00000 | $0.00892 |
| Sonnet 5 | $0.00000 | $0.00357 |
| Haiku 4.5 | $0.00000 | $0.00178 |
Grade A, and why
agent-emergency 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 11d 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 — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.
agent-emergency — agent stuck in an active loop
Why it exists (the crack between C-08 and C-12)
The existing signals cover two cases:
- C-08 — a dead / silent agent (pane = bash, no turns) → Dottore diagnosis.
- C-12 — an agent burning with
cadenza 0.00/min, zero checkpoints → kill candidate.
The third one is missing: an agent that is ALIVE and ACTIVE and REPEATS the same cycle without
producing anything. It generates turns (so it is NOT "dead" and does NOT have cadenza 0.00), but
it makes no progress. Real examples:
- two sessions bouncing ACK off each other forever (coordination ping-loop);
- a worker repeating the same query / same action to no effect;
- an agent re-processing the same undelivered message.
It used to be invisible → the Capitano never stepped in. This skill makes it detectable and manageable.
When to use it
On SUSPICION, not across the board and not on every tick. Start this procedure when you notice one of these hints (usually while doing something else): an agent that has been "working" for a while but whose queue is not shrinking / no new position changes state; or you see the same exchange repeating in the chat/pane.
1. DETERMINISTIC detection (no eyeballing)
Confirm the loop with two cheap checks — no message to the agent (do not disturb it, this is Tier-2 pull):
# (a) REPETITION — does the pane show the same exchange/output N times?
# Two captures spaced apart: if the "new" content is identical → it is repeating.
tmux capture-pane -t <SESSION> -p -S -60 > /tmp/ae_1.txt
sleep 20
tmux capture-pane -t <SESSION> -p -S -60 > /tmp/ae_2.txt
diff /tmp/ae_1.txt /tmp/ae_2.txt # little/no "real work" difference = suspected loop
# (b) 0 DB PROGRESS — is the agent "active" but moving nothing in the DB?
# If available, the by-agent observability helper (it reuses
# position_state_transitions): 0 recent transitions for this agent = no output.
python3 /app/shared/skills/db_query.py recent-activity # by_agent: 0 for the session = no output
# Generic fallback: the queue upstream of the agent does NOT shrink between two checks
# (e.g. next-for-analista unchanged while ANALISTA-N is "working").
What ships with it
6 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.
- 11d ago First seen · 128 lines · 0 tokens per session scan A 5992f0429994
agent-emergency is a skill published in the GitHub repository leopu00/job-hunter-team (49 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,783 tokens. 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
atmos-introspection
Introspection & Querying: describe/list commands, config filtering, workspace introspection, dependency graphs, YQ integration, --help= scoped CLI help.
atmos-schemas
JSON Schema for Atmos: stack-manifest and atmos.yaml config schemas, IDE auto-completion, validate stacks/schema/config, SchemaStore integration.
vs-search-tuning-partial-case
Use when the user provides 1-50 concrete bad-case search queries for one Viking Search app and wants local deterministic fixes. This skill only verifies request-level fine-operation interventions against a read-only baseline scene and delivers a console-ready configuration sheet, validated payloads, and a replay…
atmos-lint
Atmos Terraform linting with TFLint: standalone atmos terraform lint, component-aware config discovery and toolchain versions, TFLint rule configuration, and lifecycle hooks/CI findings. Use when configuring, running, debugging, or documenting Terraform/OpenTofu linting in an Atmos project.
atmos-diagnostics
Atmos diagnostics: machine-readable JSONL event streams, diagnostics.enabled/file/includeoutput, subprocess start/end/output events, masking, and debugging Atmos execution.
vs-search
Search runtime and scene management: verify queries, inspect scenes, debug app readiness, and diagnose recall or scene-config issues.