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/resilienceWrote 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/resilience)<a href="https://agentmods.dev/skills/leopu00/job-hunter-team/resilience"><img src="https://agentmods.dev/badge/skills/leopu00/job-hunter-team/resilience/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/resilience"><img src="https://agentmods.dev/badge/skills/leopu00/job-hunter-team/resilience.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Privilege Escalation · line 28 Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.Fix: Avoid sudo/root unless strictly required. Prefer least-privilege patterns. If elevation is needed, document the justification and scope.
- medium Privilege Escalation · line 31 Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.Fix: Avoid sudo/root unless strictly required. Prefer least-privilege patterns. If elevation is needed, document the justification and scope.
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 | $0.00091 | $0.01408 |
| Opus 5 | $0.00046 | $0.00704 |
| Sonnet 5 | $0.00018 | $0.00282 |
| Haiku 4.5 | $0.00009 | $0.00141 |
Grade B, and why
resilience 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 12d 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
it routes system/python/node/browser correctly and uses the `sudo apt` you already have). Then How it starts
The opening of the file, as written. The whole thing — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
resilience — never give up silently on a broken tool
Why it exists
A mission-critical tool (LinkedIn verification via Playwright) died because a system library was
missing. Agents reported "can't verify" and silently fell back to "queue empty" — the failure was
discovered downstream after hours of new=0. This skill makes tool failure loud and
recoverable instead of silent and fatal.
The core rule
A broken tool is NOT an empty result. Before you ever write "queue exhausted", new=0, or
"nothing to do", you MUST self-check the tool you depend on. If the tool is broken, you do not have
"no work" — you have a repair to do or an escalation to raise.
The fallback ladder — climb in order, stop at the first that succeeds
- Detect & classify. Tool exited non-zero / missing dependency / load error
(
exitCode 127,cannot open shared object file,command not found,error while loading shared libraries) → BROKEN. Tool ran clean and returned zero items → EMPTY (genuine). Only EMPTY justifies "no work". - Auto-repair. Restore the missing dependency via
jht-install(the canonical wrapper — it routes system/python/node/browser correctly and uses thesudo aptyou already have). Then retry the original tool. Example: browser fails withcannot load libatk-1.0.so.0→jht-installthe browser system deps (playwright install-deps/sudo apt-get installthe lib) → relaunch. - Alternative method. If the primary tool can't be repaired in-loop, switch method toward the
same goal:
- LinkedIn: use the HTTP guest fetch, or verify liveness on the company's canonical careers/ATS page (Greenhouse / Lever / Ashby / Workable). Never trust a LinkedIn HTTP 200 — the authwall returns 200 for closed jobs too.
- Mark, don't drop. If still inconclusive, leave the data state UNCHANGED and tag it
OPEN_UNVERIFIED+ aNOTE_MISMATCH. Never silently overwrite with a guess. - Escalate (within the 2-3 attempt ceiling, see below). Tool broken and not repairable in
≤2-3 shots → message the Capitano with the EXACT fix: the failing command, the missing
dependency, and the
jht-install/ Dockerfile line that resolves it. Then keep working via the alternative method (or move to another source) — do not stall, but do not push past the ceiling either.
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.
- 12d ago First seen · 93 lines · 91 tokens per session scan B 87fd9004f489
resilience is a skill published in the GitHub repository leopu00/job-hunter-team (49 stars, last pushed yesterday), licensed MIT. It adds 91 tokens to every session and 1,408 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it B with 1 finding (asks for root). 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.