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 reggiechan74/JobOps --skill coverlettergit clone --depth 1 https://github.com/reggiechan74/JobOpsWrote 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/reggiechan74/jobops/coverletter)<a href="https://agentmods.dev/skills/reggiechan74/jobops/coverletter"><img src="https://agentmods.dev/badge/skills/reggiechan74/jobops/coverletter/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/reggiechan74/jobops/coverletter"><img src="https://agentmods.dev/badge/skills/reggiechan74/jobops/coverletter.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 | $0.00018 | $0.04615 |
| Opus 5 | $0.00009 | $0.02308 |
| Sonnet 5 | $0.00004 | $0.00923 |
| Haiku 4.5 | $0.00002 | $0.00462 |
Grade A, and why
coverletter 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 — 238 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Configuration
Read .jobops/config.json. If missing, stop with:
JOBOPS NOT CONFIGURED Run /jobops:setup to initialize your workspace.
Use config.directories.<key> for all file paths in this skill.
Use config.preferences.cultural_profile if this skill generates resume-style content.
Use config.preferences.default_jurisdiction if this skill has jurisdiction-sensitive logic (crisis/legal skills accept --jurisdiction=<ISO-3166-2> to override).
Cover letter mode
Resolve the effective mode: the --mode= flag if present and valid, else config.preferences.cover_letter_mode, else retrospective (a config written before this key existed has no cover_letter_mode; treat the absence as retrospective). Reject an invalid --mode= value with: Invalid --mode value. Use retrospective or forward.
- retrospective → dispatch the
step4-cover-letteragent (Step 3 below), unchanged. - forward → run the forward intake interview, then dispatch the
step4-cover-letter-forwardagent.
Forward intake interview (mandatory for forward mode)
Forward mode never drafts without this interview, because the agent runs non-interactively and cannot ask the candidate anything mid-run. Before dispatch:
- Prime the problem set cheaply. Read the JD ($2) and, if it exists, the specialist files under
{config.directories.company_intelligence}/{Company}/(corporate.md,legal.md,leadership.md,market.md). Do not run web searches here — the agent's Step 3a pipeline does the deep verification. Summarize the candidate-facing problem set in 2–4 bullets so the candidate reacts to evidence rather than inventing problems. - Ask the five questions, one at a time, in the main conversation:
- Role thesis / problem set — given the primed bullets, what is this role actually there to solve?
- First-90-days actions — the 2–3 things you'd do first to address that problem set, plus one line on the 6–12 month arc.
- Per-action proof — for each action, the past work that backs your ability to do it.
- Gap & plan — the real gap you carry and how you'd work with it (without trivializing it as quickly closeable).
- Company-specific notes — anything about the firm's situation to reflect in the context paragraph or problem set.
- If the candidate declines or abandons the interview, do not draft. Tell them forward mode requires the interview, and that retrospective mode (
--mode=retrospective) produces a letter without one. - Pass the answers and the primed problem set inline to the
step4-cover-letter-forwardagent in its dispatch prompt.
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 · 238 lines · 18 tokens per session scan A 9d6f7d7eb1c2
coverletter is a skill published in the GitHub repository reggiechan74/JobOps (25 stars, last pushed 3mo ago), licensed MIT. It adds 18 tokens to every session and 4,615 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…