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 pm-job-searchWrote 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/setup)<a href="https://agentmods.dev/skills/archugunov/pm-job-search/setup"><img src="https://agentmods.dev/badge/skills/archugunov/pm-job-search/setup/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/setup"><img src="https://agentmods.dev/badge/skills/archugunov/pm-job-search/setup.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 | $0.00129 | $0.08934 |
| Opus 5 | $0.00064 | $0.04467 |
| Sonnet 5 | $0.00026 | $0.01787 |
| Haiku 4.5 | $0.00013 | $0.00893 |
Grade A, and why
setup 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 10d 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 — 594 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/setup — first-run install and re-configure
Onboard the user onto pm-job-search by filling in userdata/profile.md and scaffolding the rest of the userdata tree. Idempotent — safe to re-run.
Voice: every prompt and message in this skill follows the plugin's tone-of-voice + low-effort-first guidelines in ${CLAUDE_PLUGIN_ROOT}/TONE.md. TONE.md governs; the quoted lines below are examples of what a step should get at and roughly how it should sound, not strings to recite.
The wording used to be locked — "use it verbatim, not paraphrased". That is why this file could teach a defect: a locked example outranks the rule it breaks, and every leak the corpus records at the confirm-a-write moment traces to one. What must not drift is the order of the steps, what each one asks, and the things each step is explicitly told not to do. The sentence itself is yours.
If an example and TONE.md disagree, TONE.md wins and the example is a bug —
fix it here rather than following it.
Interaction form is not wording, and it does not unlock. A step that says
"single-select via AskUserQuestion" gets a select; a step that says explicitly
NOT to use one stays prose. Unlocking the sentence unlocked the shape too on the
first run afterwards — geography came back as an open-ish prose question — so it
is worth stating separately. Where AskUserQuestion is unavailable, prose that
offers the same closed set of named choices is an acceptable substitute; an open
question is not.
Opening line (after Step 0, fresh install only):
"OK, let's get you set up — nine quick steps, none of it locked in."
Do NOT wait for a confirmation. Go straight into Step 1 in the same message. The
user has already chosen to run this skill; asking "Ready?" spends one of their
turns on a decision they have made, which TONE.md names as an anti-pattern.
Mode detection
Run this BEFORE asking the first question:
- If
userdata/profile.mdexists → enter re-run mode: read the file, ask "keep current / update / skip" per field, never wipe existing answers. - If
userdata/profile.mddoes NOT exist → enter fresh-install mode: walk all nine steps in order. --refreshflag → re-run mode, but only re-resolve the workspace-rootCLAUDE.mdfrom the template using the currentprofile.mdcontent. Skip all questions. Useful after manual edits to profile.md.
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.
- 10d ago First seen · 594 lines · 129 tokens per session scan A 64d5659b8d95
setup is a skill published in the GitHub repository archugunov/pm-job-search (7 stars, last pushed 14d ago), licensed MIT. It adds 129 tokens to every session and 8,934 once invoked, about $0.0006 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 2026-08-31.
Other skills, from other repositories
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:save
The human wants to checkpoint. Or: the stash has grown heavy — 5+ items, 30+ minutes, a natural pause in the work. The squirrel doesn't decide when to save. It surfaces the need and lets the human pull the trigger. Runs the full save protocol: confirms stash, writes log, updates state, generates projections…
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.
alive:system-cleanup
The world feels messy. Stale tasks, orphan folders, v2 remnants, unsaved sessions — entropy is accumulating and needs to be addressed before it compounds. Scans across all walnuts, then surfaces issues one at a time.
alive:create-walnut
Something new is emerging. A venture, an experiment, a person entering the orbit, a life area getting serious. It needs its own walnut — its own identity, history, and future. Scaffolds the full structure, maps existing context sources, and optionally migrates files across.
alive:session-history
Revive sessions (quick or heavy), browse, and search — 'what happened recently?', 'find the session where we discussed X', 'revive yesterday's session'. For single-session recall and multi-session browsing. If the human needs to merge multiple sessions into one working context or detect conflicts between parallel…