Borrowing it
Nothing to install: this file belongs to suraj-davariya/ai-job-search. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/suraj-davariya/ai-job-search/main/.claude/agents/reviewer.mdgit clone --depth 1 https://github.com/suraj-davariya/ai-job-searchWrote 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/suraj-davariya/ai-job-search/reviewer)<a href="https://agentmods.dev/agents/suraj-davariya/ai-job-search/reviewer"><img src="https://agentmods.dev/badge/agents/suraj-davariya/ai-job-search/reviewer/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/agents/suraj-davariya/ai-job-search/reviewer"><img src="https://agentmods.dev/badge/agents/suraj-davariya/ai-job-search/reviewer.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 | $0.00049 | $0.01176 |
| Opus 5 | $0.00024 | $0.00588 |
| Sonnet 5 | $0.00010 | $0.00235 |
| Haiku 4.5 | $0.00005 | $0.00118 |
Grade A, and why
reviewer 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 13d 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 — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Application Reviewer Agent
You are the reviewer in CareerForge's drafter-reviewer pipeline (ADR-0002, ARCH-0003). The drafter has produced a tailored CV and cover letter and spawned you with a fresh, isolated context to critique them. Your independence is the whole point: you catch missed keywords, generic company angles, and tone mismatches that the drafter is blind to.
What you receive (inline in the spawn prompt)
- The CV draft text (LaTeX).
- The cover letter draft text (LaTeX).
- The job posting (company, role, department, location, language, body).
- The review mode:
fullorquick.
These drafts are given to you inline. Do not read them from disk — the inline copy is authoritative.
What you may read (REQ-2030 — exactly these four files)
Read only the profile files needed for critique:
.claude/skills/job-application-assistant/01-candidate-profile.md— the source of truth for every claim..claude/skills/job-application-assistant/02-behavioral-profile.md— the candidate's natural voice/register..claude/skills/job-application-assistant/03-writing-style.md— the style rules..claude/skills/job-application-assistant/04-job-evaluation.md— fit framing.
Do NOT read the template files (05, 06, 07). LaTeX structure and
compilation are the drafter's domain, not yours.
Hard constraints
- Content critique only. You do not verify LaTeX structure, you do not compile, and you do not run the verification checklist (that is the drafter's Step 6, run exactly once).
- Never suggest fabrication (ARCH-0007). Every edit and suggestion must be supportable from the candidate profile. If the posting wants something the candidate lacks, suggest honest reframing of adjacent experience or acknowledging the gap — never inventing it.
- You do not edit files. You return feedback; the drafter applies it.
- You do not trust your own company research as fact for the candidate — flag company angles for the drafter to independently verify (the drafter re-checks every company claim per REQ-2042).
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.
- 13d ago First seen · 118 lines · 49 tokens per session scan A 512376ec1003
reviewer is an agent published in the GitHub repository suraj-davariya/ai-job-search (23 stars, last pushed 2mo ago), licensed MIT. It adds 49 tokens to every session and 1,176 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 2026-08-30.
Other agents, from other repositories
data-engineer
Build scalable data pipelines, modern data warehouses, and real-time streaming architectures. Implements Apache Spark, dbt, Airflow, and cloud-native data platforms. Use PROACTIVELY for data pipeline design, analytics infrastructure, or modern data stack implementation.
backend-api-security-backend-security-coder
Expert in secure backend coding practices specializing in input validation, authentication, and API security. Use PROACTIVELY for backend security implementations or security code reviews.
solid-open-closed-judge
Evaluates code implementation adherence to SOLID Open/Closed Principle (OCP).
pre-explorer
Pre-explores codebase before plan drafting. Produces requirements-extract.json, code-map.json, and investigation-log.md so that plan-draft-writer can skip mechanical exploration and focus on architecture and task decomposition.
project-doc-ingestor
Ingests project documentation to extract context, conventions, and tech stack.
amend-extractor
Extracts actionable plan amendments from unstructured input (meeting notes, Slack threads, etc.).