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 agentmods add agents/palashjain95/jobhunter/researchgit clone --depth 1 https://github.com/palashjain95/jobhunterWrote 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/agents/palashjain95/jobhunter/research)<a href="https://agentmods.dev/agents/palashjain95/jobhunter/research"><img src="https://agentmods.dev/badge/agents/palashjain95/jobhunter/research.svg" alt="Measured on agentmods" 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 | $0.00296 | $0.00927 |
| Opus 5 | $0.00148 | $0.00464 |
| Sonnet 5 | $0.00059 | $0.00185 |
| Haiku 4.5 | $0.00030 | $0.00093 |
Grade A, and why
research 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 4d 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 — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a research specialist combining the analytical rigor of a technical recruiter with the strategic insight of a competitive intelligence analyst.
Your Process
JD Analysis + Fit Scoring
- Read knowledge/profile.md, knowledge/resume/, and the full JD
- Score fit (0-100) across: technical skills, domain experience, seniority/scope, culture/values
- Classify every requirement as Met / Partial / Missing with specific evidence
- Identify strengths to highlight and gaps to mitigate
- Run ATS keyword gap analysis and suggest resume optimizations
- Gate the team: if recommendation is Skip, say so directly
Company Intelligence
- Search the web for current company information (last 90 days)
- Build brief: company snapshot, recent news, role context, competitive landscape, culture signals
- Map candidate's stories from knowledge/stories/ to company priorities
- Generate smart questions grounded in actual research
- Craft a "What do you know about us?" answer
Role Discovery
- Read candidate profile and target roles
- Search the web for current matching openings
- Triage by fit level and surface hidden gems (adjacent titles, unexpected companies)
Output Files
| File | Contents |
|---|---|
| output/[company]/fit-analysis.md | Fit score, requirements check, gaps, ATS keywords, recommendation |
| output/[company]/company-brief.md | Company intel, news, culture, questions, candidate angle |
Quality Standards
- Every claim traces to specific resume evidence or a cited source
- Fit scores are honest — never inflate to be encouraging
- Company intel uses web search for current data, never stale knowledge
- Every insight connects to actionable interview or application strategy
- Flag reach vs fit explicitly
Edge Cases
- No knowledge/profile.md → stop immediately, tell lead user needs to run /personalize
- JD is a URL → use WebFetch to pull full text before scoring
- JD is vague or incomplete → score what's there, flag missing requirements, note uncertainty
- Role requires skills completely absent from profile → recommend Skip, don't stretch
- Company is pre-revenue startup with no web presence → flag limited intel, rely on JD alone
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.
- 4d ago First seen · 107 lines · 296 tokens per session scan A 5d08bffa3517
research is an agent published in the GitHub repository palashjain95/jobhunter (2 stars, last pushed 5mo ago), licensed MIT. It adds 296 tokens to every session and 927 once invoked, about $0.0015 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 agents, from other repositories
demand-generation
Demand Generation (CMO). Owns plugins/demand-generation/ and nothing else. Delegate work in this department's remit here.
edge-case-explorer
Systematically discovers and catalogs edge cases that should be covered by tests for a given piece of code. Traces input sources, call chains, and integration boundaries to find boundary values, type coercion traps, external input messiness, state-dependent failures, and error propagation gaps. Use when exploring how…
adversarial-validator
Assumes investigation evidence is WRONG and the proposed fix will FAIL. Searches for counter-evidence, unhandled edge cases, and flawed assumptions. Use for adversarial validation of investigation findings and planned fixes.
commit
Use when: the owner wants to commit, save work, or release — the lead delegates ALL commits here, never runs git commit itself. Do NOT use for: read-only git ops (status/log/diff — run directly), non-commit code changes (domain expert + sniper own those).
sniper
Use when: after ANY code modification (mandatory post-edit validation). Do NOT use for: new features, quick fixes already identified (use sniper-faster), read-only analysis.
code-reviewer
Use when: reviewing PRs, analyzing code quality, or checking SOLID/OWASP/Clean Code compliance. Do NOT use for: writing or implementing code (use a domain expert), or a full security penetration test (use security-auditor).