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 jain777/jobclaw-skills --skill infer-statusgit clone --depth 1 https://github.com/jain777/jobclaw-skillsWrote 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/jain777/jobclaw-skills/infer-status)<a href="https://agentmods.dev/skills/jain777/jobclaw-skills/infer-status"><img src="https://agentmods.dev/badge/skills/jain777/jobclaw-skills/infer-status/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/jain777/jobclaw-skills/infer-status"><img src="https://agentmods.dev/badge/skills/jain777/jobclaw-skills/infer-status.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 | $0.00075 | $0.01478 |
| Opus 5 | $0.00037 | $0.00739 |
| Sonnet 5 | $0.00015 | $0.00296 |
| Haiku 4.5 | $0.00007 | $0.00148 |
Grade A, and why
infer-status 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 — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.
infer-status
Map signals → status using the taxonomy decision table — no invention. Hard rules: ../_shared/RULES.md. All enums, the decision table, the ghosting rule, and the offer-accept guardrail live in ../../knowledge/status/taxonomy.md.
Inputs
Per-application signals (JSON; single or array)
{
"job": { "company": "...", "role": "...", "job_id": "..." },
"current_status": "applied | screening | assessment | interview | final-round | offer | accepted | rejected | withdrawn | ghosted",
"triage_class": "rejection | screen | interview-invite | assessment | offer | recruiter-outbound | info | request-info | spam | other | null",
"days_since_apply": "number | null",
"days_since_last_contact":"number | null",
"portal_state": "string | null", // verbatim portal label if scraped, e.g. "Application Rejected"
"as_of": "YYYY-MM-DD"
}
Or --in inbox/triage-<date>.json to read triage records directly; the skill joins triage → applications by (company, role) or job_id and pulls current_status from tracker.json if present.
Flags
--ghost-days N— override the 14-day ghosting threshold.--update tracker.json— write the new status back intotracker.json(only fields that changed).--confirm-accept— the only way to transitionoffer → accepted. Without it, an offer stays atoffer.
Method
-
Read the taxonomy decision table and the ghosting rule.
-
Resolve
triage_classif absent by reading the latestinbox/triage-<date>.jsonfor this job (if present). Otherwise skip the email branch and use only portal + recency signals. -
Apply the decision table.
(triage_class × current_status) → (next_status, suggested_action). Terminal email classes (rejection,offer) trump current status;info/request-info/spamnever change status. -
Override on portal signal if present. Portal labels are ground truth when they exist (e.g.,
portal_state: "Application Rejected"→rejectedregardless of email). Record the override inrationale.
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 · 105 lines · 75 tokens per session scan A e129734f5938
infer-status is a skill published in the GitHub repository jain777/jobclaw-skills (5 stars, last pushed 3mo ago), licensed MIT. It adds 75 tokens to every session and 1,478 once invoked, about $0.0004 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
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
agentmail
Use your assigned AgentMail inbox to read email tasks, explicitly send or reply, and check delivery. Provided automatically by your inbox assignment.
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
peekaboo
Capture and automate macOS UI with the Peekaboo CLI.