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 akiotanaka847/qaio-desktop --skill source-candidatesgit clone --depth 1 https://github.com/akiotanaka847/qaio-desktopWrote 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/akiotanaka847/qaio-desktop/source-candidates)<a href="https://agentmods.dev/skills/akiotanaka847/qaio-desktop/source-candidates"><img src="https://agentmods.dev/badge/skills/akiotanaka847/qaio-desktop/source-candidates/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/akiotanaka847/qaio-desktop/source-candidates"><img src="https://agentmods.dev/badge/skills/akiotanaka847/qaio-desktop/source-candidates.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 | $0.00065 | $0.01254 |
| Opus 5 | $0.00032 | $0.00627 |
| Sonnet 5 | $0.00013 | $0.00251 |
| Haiku 4.5 | $0.00006 | $0.00125 |
Grade A, and why
source-candidates 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 6d 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 — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Source Candidates
When to use
- Explicit: "find candidates for {role}", "source engineers from GitHub", "build a sourcing list for {role}", "source 20 candidates for {role} from {signal}".
- Rubric-seed variant: "update the rubric for {role}", "set the must-haves for the {role} req" - ask once for level target, top 3 must-haves, top 3 nice-to-haves, 2-3 red flags, write
reqs/{role-slug}.md, then stop (skip the scrape) so every other hiring skill reads the rubric first. - Implicit: kicked off by founder at start of hiring push, or during req-planning session.
- Safe per-role per-signal. Keep lists short (≤ 30 per pass) so rankings meaningful.
Connections I need
I run external work through Composio. Before this skill runs I check that the categories below are linked. Missing → I name the category, ask you to connect it from the Integrations tab, stop.
- Web scrape (Firecrawl) — pull public profiles and signal pages. Required.
- Engineering (GitHub) — score OSS contributors and read repo signal. Required when source is GitHub.
- Web scrape (LinkedIn) — score public LinkedIn profiles. Required when source is LinkedIn.
- ATS (Ashby, Greenhouse, Lever, Workable) — dedupe against existing pipeline. Optional.
If none of the required categories are connected I stop and ask you to connect Firecrawl first.
Information I need
I read your people context first. For every required field that's missing I ask ONE plain-language question (best modality: connected app > file drop > URL > paste) and wait.
- Role rubric — Required. Why I need it: I score every candidate against your must-haves. If missing I ask: "What role are we sourcing for, what level, and what are your top three must-haves?"
- Signal source — Required. Why I need it: I need a place to pull names from. If missing I ask: "Where should I source from, a GitHub org, a LinkedIn search, a community list, or a conference attendee list?"
- Companies to exclude — Optional. Why I need it: keeps people you've already passed on out of the list. If you don't have it I keep going with TBD.
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.
- 6d ago First seen · 60 lines · 65 tokens per session scan A 05045ff13385
source-candidates is a skill published in the GitHub repository akiotanaka847/qaio-desktop (2 stars, last pushed 8d ago), licensed MIT. It adds 65 tokens to every session and 1,254 once invoked, about $0.0003 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 2026-09-05.
Other skills, from other repositories
inspiring-and-retaining
Equips founders with practical retention and inspiration techniques grounded in selfless leadership, strategic kindness, and relationship maintenance at scale. Covers making it about the audience (not you), the random-act-of-kindness mood reset, the homelessness perspective technique, praise-to-criticism ratios…
influencing-and-persuading
Provides founders with Socratic influence techniques, confidence projection methods, and patience-based persuasion strategies for converting stakeholders without overt selling. Covers idea-seeding (making others believe your idea is theirs), the paradox of persuasion (listening as the primary influence tool)…
resolving-people-conflict
Delivers specific behavioural systems for resolving interpersonal conflict in real time -- reframing conflict as a helping stance, the 24-hour cooling rule, strategic surrender of what cannot be controlled, and the bulletproof vest protocol (a structured seven-step system for safe conflict resolution). Use when a…
teaching-and-leading
Guides founders in leading through modelling behaviour, coaching (not managing), leveraging mirror neurons for mood contagion, distributing leadership titles generously, and using gratitude as a pre-meeting performance enhancer. Covers showing rather than telling, strengths-based leadership, the coach-and-student…
role-credential-readiness
Flag credentials a role legally requires.
workforce-intake-packet
Assemble workforce intake packets.