trackly

A job-search tool for finding current openings and companies, reviewing job details, and saving jobs the user selects.

In plain words
What is it for?
It helps search by role, location, remote status, company, and recency, inspect job summaries, discover companies, and track chosen jobs.
Why use it?
It keeps job searches tied to the service's current records and preferences, while avoiding unsupported claims about posting dates or application status.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/trackly-app/trackly-cli/trackly
Any agent
npx skills add trackly-app/trackly-cli --skill trackly
Clone the repo
git clone --depth 1 https://github.com/trackly-app/trackly-cli

Made for: Claude Code, Codex.

Per session 44 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 371 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00044 $0.00371
Opus 5 $0.00022 $0.00186
Sonnet 5 $0.00009 $0.00074
Haiku 4.5 $0.00004 $0.00037

Measured 2d ago against content hash d99d7bd35600, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

trackly 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 2d 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.

plugins/trackly/skills/trackly/SKILL.md · 24 lines

What it actually says

trackly

Use trackly as the source of truth for current openings, monitored companies, saved jobs, and discovery preferences.

Search workflow

  1. If the request depends on saved preferences, call trackly_get_preferences before searching. Do not invent a preference that is missing.
  2. Call trackly_search_jobs with the user's explicit constraints. Preserve recency, location, remote, company, and role constraints exactly.
  3. Use trackly_search_companies only when company discovery or company identity is part of the request.
  4. Use trackly_get_job for the exact posting record and trackly_get_job_brief for a decision-ready summary. Treat postedLast7d and latestPostedAt as validated posting-date signals only; never substitute first-seen time for a posting date.
  5. Present returned facts as returned by trackly. Label any model inference as an inference and never imply a posting is still open when trackly reports otherwise.
  6. Call trackly_update_status only after the user chooses a job or explicitly asks to update its status. Marking a job applied additionally requires Apply write permission because it reconciles the application run; never use it to infer or claim submission.

Do not rescore an approved application inside this discovery skill. When the user asks to fill an approved application, use the trackly-apply skill.

Scope boundary

This plugin supports job and company search, job briefs, tracking, and application filling. Employee discovery and referral intelligence are outside its scope.

Files

What ships with it

1 file 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.

Changes

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.

  1. 2d ago First seen · 24 lines · 44 tokens per session scan A d99d7bd35600

Subscribe to this mod's changes

trackly is a skill published in the GitHub repository trackly-app/trackly-cli (3 stars, last pushed 3d ago), licensed MIT. It adds 44 tokens to every session and 371 once invoked, about $0.0002 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.