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/pipeline-triageWrote 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/pipeline-triage)<a href="https://agentmods.dev/skills/leopu00/job-hunter-team/pipeline-triage"><img src="https://agentmods.dev/badge/skills/leopu00/job-hunter-team/pipeline-triage/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/pipeline-triage"><img src="https://agentmods.dev/badge/skills/leopu00/job-hunter-team/pipeline-triage.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 4 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 Prompt Injection · line 69 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Prompt Injection · line 92 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Prompt Injection · line 105 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Prompt Injection · line 75 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
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 | $0.00157 | $0.02819 |
| Opus 5 | $0.00078 | $0.01409 |
| Sonnet 5 | $0.00031 | $0.00564 |
| Haiku 4.5 | $0.00016 | $0.00282 |
Grade A, and why
pipeline-triage 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 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.
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 — 153 lines — stays where its author put it; the contents beside it link to each section on GitHub.
pipeline-triage — data-driven scaling
The pipeline is a dynamic system. Each role consumes very differently per task — adding a 2nd Writer costs much more than adding a 2nd Scout. Scaling at the head when the bottleneck is at the tail produces more backlog, not more output. Always start from the data.
When to open this skill (bug #17)
You open it on observed conditions, not only on explicit Sentinella orders. Triggers:
- Velocity team below 50% of target
- Any role queue at 0 (Scout exhausted, Scorer/Writer idle)
- Scout sources reported exhausted ("bebee, indeed, glassdoor — nothing new")
[SCALA UP]from SentinellaMARGINE/PIPELINE VUOTA + UNDERSHOOTfrom bridge-pacing- Cold start of a window
The historical anti-pattern: Capitano sees SCRITTORE_QUEUE=0 +
PROMOTABLE_40_49=6, describes the situation perfectly to the
user, does not run the promotion. This skill is active, not
advisory — when conditions match, you execute.
Step 1 — read the backlog (always, before any spawn)
python3 /app/shared/skills/db_query.py stats
From positions (P), scores (S), applications (A), compute:
| Metric | Formula | What it means |
|---|---|---|
| UNSCORED | P − S | positions the Scorer still has to evaluate |
| DRAFT_BLOCKED | applications with status = draft |
Writer ↔ Critic loop stalled |
| SCRITTORE_QUEUE | positions with score ≥ 50 AND no application |
Writer queue (real demand for new CVs) |
| PROMOTABLE_40_49 | positions with score 40-49 AND no application |
parking band — promotable on demand |
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 · 153 lines · 157 tokens per session scan A 25e44bffab6c
pipeline-triage is a skill published in the GitHub repository leopu00/job-hunter-team (49 stars, last pushed yesterday), licensed MIT. It adds 157 tokens to every session and 2,819 once invoked, about $0.0008 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 2026-08-30.
Other skills, from other repositories
gws-tasks
Google Tasks: Manage task lists and tasks.
gws-workflow-standup-report
Google Workflow: Today's meetings + open tasks as a standup summary.
persona-customer-support
Manage customer support — track tickets, respond, escalate issues.
persona-event-coordinator
Plan and manage events — scheduling, invitations, and logistics.
persona-project-manager
Coordinate projects — track tasks, schedule meetings, and share docs.
persona-sales-ops
Manage sales workflows — track deals, schedule calls, client comms.