Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add archugunov/pm-job-search/plugin install job-sweepWrote 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/archugunov/pm-job-search/sweep)<a href="https://agentmods.dev/skills/archugunov/pm-job-search/sweep"><img src="https://agentmods.dev/badge/skills/archugunov/pm-job-search/sweep/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/archugunov/pm-job-search/sweep"><img src="https://agentmods.dev/badge/skills/archugunov/pm-job-search/sweep.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00128 | $0.03519 |
| Opus 5 | $0.00064 | $0.01759 |
| Sonnet 5 | $0.00026 | $0.00704 |
| Haiku 4.5 | $0.00013 | $0.00352 |
Grade C, and why
sweep scanned grade C 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.
Hidden instructionshighPrompt injection
Directives inside HTML comments, invisible characters or bidirectional overrides are read by the model and not by the person reviewing the file.
<!-- job-sweep's whole profile. Edit any line and the next sweep picks it up. Delete this file to start over. Add companies_of_interest: [Company A, Company B] yourself to get one extra site: query per named company on e How it starts
The opening of the file, as written. The whole thing — 333 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/job-sweep:sweep — find open product roles that match you
Discovery, and nothing else. This plugin does not track applications, score against a rubric, or keep company folders. It finds roles and remembers what it already showed you.
Voice: every prompt and message in this skill follows
${CLAUDE_PLUGIN_ROOT}/references/TONE.md — plain prose not fenced blocks, one
ask per message, no "since last time" prompts on a first run, and every chat
summary inside Rule D's skim budget. The exact wording of each question below is
locked-in; use it verbatim, not paraphrased.
State
Two files, in a job-sweep/ folder in the user's working directory:
job-sweep/profile.md— frontmatter only. Keys:target_titles,target_industries,geography: {mode, mode_detail}, and optionalcompanies_of_interest.job-sweep/seen-roles.jsonl— append-only, one JSON object per line.
Never write anywhere else. No userdata/, no company folders.
Mode detection
Run before anything else:
job-sweep/profile.mdexists → sweep mode. Read it and go straight to "Running the sweep". Do NOT re-ask the onboarding questions, and do NOT ask what changed since last time — the profile is the answer.- It does not exist → first-run mode. Walk the onboarding below, then sweep in the same session.
First run
Create job-sweep/ first, so there is somewhere to drop a CV, then ask:
"First sweep — I need three things: what roles you want, what industries, and where you'll work. Drop a CV into
job-sweep/as cv.md, cv.txt or cv.pdf and I'll read them off it, or just answer three questions. Which?"
Use AskUserQuestion with two options: I'll drop a CV / Ask me the three questions.
CV path
Follow ${CLAUDE_PLUGIN_ROOT}/references/cv-extraction.md § "Finding the CV",
checking job-sweep/cv.md, job-sweep/cv.txt, job-sweep/cv.pdf in that order.
State directory: job-sweep/ — already created above in "First run", so there
are no scaffold files left to create here. Its § "The governing rule" applies in
full: never fill a field the CV does not
contain. A CV with no clear location means you ask where they'll work — it does
not mean guessing from the most recent employer's address.
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 · 333 lines · 128 tokens per session scan C c29d811af876
sweep is a skill published in the GitHub repository archugunov/pm-job-search (7 stars, last pushed 17d ago), licensed MIT. It adds 128 tokens to every session and 3,519 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it C with 1 finding (hidden instructions). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
chapter-writing
This skill should be used when the user asks to "write a chapter", "next chapter", "chapter outline", "draft chapter", "continue the story", "write a scene", "outline a chapter", or wants to write prose for a story project.
story-init
This skill should be used when the user asks to "start a new story", "initialize a story project", "create a story", "new book", "set up a story", or wants to begin a new fiction writing project from scratch.
revision-continuity
This skill should be used when the user asks to revise a chapter, edit prose, continuity check, find inconsistencies, audit character state, check timeline consistency, line edit, developmental edit, polish a draft, or prepare existing story material for the next revision pass.
story-maintenance
This skill should be used when the user asks to validate, reindex, repair registries, check links, check continuity, count words, summarize a story project, import an existing manuscript, export a manuscript, run the story CLI, or perform deterministic maintenance on a Story Skills markdown project.
alive:demo
Generate a believable, lived-in ALIVE world from a free-text persona description (custom path) or a deterministic sandbox preset. Routes the create/list/activate/deactivate/delete/status surface and orchestrates the 5-stage subagent generation pipeline.
alive:system-upgrade
Upgrade ALIVE to the current version. Handles v1/v2/v3.x source states, multi-surface aware (alive-mcp / Hermes / Codex), retroactive version detection, partial-failure resume, dry-run previews, and rollback inspection.