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 suxrobGM/jobpilot --skill rescan-skippedgit clone --depth 1 https://github.com/suxrobGM/jobpilotWrote 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/suxrobgm/jobpilot/rescan-skipped)<a href="https://agentmods.dev/skills/suxrobgm/jobpilot/rescan-skipped"><img src="https://agentmods.dev/badge/skills/suxrobgm/jobpilot/rescan-skipped/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/suxrobgm/jobpilot/rescan-skipped"><img src="https://agentmods.dev/badge/skills/suxrobgm/jobpilot/rescan-skipped.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, 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 Data Exfiltration · line 13 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
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 | $0.00049 | $0.01107 |
| Opus 5 | $0.00024 | $0.00553 |
| Sonnet 5 | $0.00010 | $0.00221 |
| Haiku 4.5 | $0.00005 | $0.00111 |
Grade A, and why
rescan-skipped scanned grade A 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
Follow `../_shared/setup.md`. Fetch the campaign: `curl -fsS -H "authorization: Bearer $JOBPILOT_API_TOKEN" "$JOBPILOT_API/api/campaigns/<campaign-id>"`. Threshold = `config.minScore` (fallback `autoApply.minMatchScore`, How it starts
The opening of the file, as written. The whole thing — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Rescan Skipped - Recover Wrongly-Dropped Jobs
Re-score a campaign's skipped jobs and set eligible ones to approved. Never apply and never change the campaign's status - apply the promoted jobs afterward via the apply skill (apply campaign <campaign-id>) or the campaign page.
Setup
Follow ../_shared/setup.md. Fetch the campaign: curl -fsS -H "authorization: Bearer $JOBPILOT_API_TOKEN" "$JOBPILOT_API/api/campaigns/<campaign-id>". Threshold = config.minScore (fallback autoApply.minMatchScore, else 60).
Step 1: Select Targets
Targets are every status:"skipped" job; with --jobs key1,key2,…, restrict to those keys.
- Always leave (permanent) - only these:
skipReasonstartingAlready applied,CAPTCHA,Payment required, orNo visa sponsorship (JD:, or one stating a JD-cited citizenship/clearance requirement. - Whole-campaign mode (no
--jobs): also leave deliberate user choices -Removed by user,Not selected by user,User cancelled…,Max applications limit reached,Campaign paused by user. --jobsmode: reconsider every named target except the permanent ones.
Count the full target list up front and process every one. Below-threshold, zero-score, and no-skipReason jobs are all targets - the stored score came from the campaign that wrongly skipped them, so it's never a reason to skip the re-score. Don't cherry-pick the jobs already at/above threshold.
Step 2: Per Job
-
Digest - parse the cached
digest. Rich = non-emptyskillsandrequirements/responsibilities. -
Re-read only when needed - if the digest is thin/empty, or the original
skipReasonwas invalid (location/onsite, sparse JD, 1099, seniority), open the posting (browser_navigate+ narrowedbrowser_snapshot; log in via../_shared/auth.mdif walled) and rebuild the digest. Send that digest and posting text with the rescan command below; terminal rows cannot be PATCHed. -
Re-score - every target gets a fresh
POST /api/score-fitwith{digest, minScore:<threshold>}; never reuse the storedmatchScore. Take the returnedscoreas-is whenverdictistrust; ondeliberate, reason fromstrongMatches/partialMatches/gaps. A zero/low score with noskipReason(common at defense/federal employers) is not a disqualifier - only a JD-stated citizenship/clearance or no-sponsorship bar is (never infer from industry). -
Decide:
- Eligible and
score >= threshold→ promote (no apply):
- Eligible and
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 · 53 lines · 49 tokens per session scan A 06552688c67d
rescan-skipped is a skill published in the GitHub repository suxrobGM/jobpilot (67 stars, last pushed 2d ago), licensed MIT. It adds 49 tokens to every session and 1,107 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (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
session-deep-dive
Deep qualitative analysis of high-signal sessions. Spawns subagents with v2 template, synthesizes patterns, compares against known findings. Use after /session-scan.
brainstorm
Brainstorm Elixir/Phoenix features — explore ideas, compare approaches, gather requirements. Use when vague idea, not sure how to approach, or want to discuss before plan.
elixir-idioms
OTP/BEAM patterns and Elixir idioms — GenServer, Supervisor, Task, Registry, pattern matching, with chains, pipes. Use when designing processes or debugging BEAM issues.
tidewave-integration
Tidewave MCP runtime tools — debugging, smoke testing, live state inspection, SQL queries, hex docs. Use when evaluating code in a running Phoenix app.
plugin-dev-workflow
Guide plugin development workflow — editing skills, agents, hooks, or eval framework in this repo. Use when modifying files in plugins/elixir-phoenix/, lab/eval/, or lab/autoresearch/. Ensures changes pass eval, lint, and tests before committing.
security
Enforce Elixir/Phoenix security — auth, OAuth, sessions, CSRF, XSS, SQL injection, input validation, secrets. Use when editing auth files, login flows, RBAC, or API keys.