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 mperkhou/career-agent-workbench --skill manual-resume-passthroughgit clone --depth 1 https://github.com/mperkhou/career-agent-workbenchWrote 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/mperkhou/career-agent-workbench/manual-resume-passthrough)<a href="https://agentmods.dev/skills/mperkhou/career-agent-workbench/manual-resume-passthrough"><img src="https://agentmods.dev/badge/skills/mperkhou/career-agent-workbench/manual-resume-passthrough/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/mperkhou/career-agent-workbench/manual-resume-passthrough"><img src="https://agentmods.dev/badge/skills/mperkhou/career-agent-workbench/manual-resume-passthrough.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 | $0.00064 | $0.00539 |
| Opus 5.5 | $0.00026 | $0.00216 |
| Sonnet 5.5 | $0.00013 | $0.00108 |
| Haiku 4.5 | $0.00006 | $0.00054 |
Grade A, and why
manual-resume-passthrough 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 2mo 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 — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Manual Resume Passthrough
Follow root AGENTS.md. Resolve all application and profile state through the
ignored bootstrap/private workspace; never pass private content or identifiers
through process arguments, public logs, tests, or commits.
Preconditions
- The exact application row exists with usable JOD and evidence state.
v1andv2exist when the governed manual workflow depends on them.- The configured MRO and human source are current.
- The requested profile is exactly
economy,regular, orpremium.
Profiles are execution policy, not variant keys. regular is the normal
gpt-5.6-sol/high policy. All profiles write the same manual row, preserve
v1 and v2, and leave explicit selection unchanged. Automatic preference is
manual > v2 > v1.
Workflow
-
Inspect the coherent workflow snapshot, v2 evidence/critique, ATS diagnostics, selected JOD, MRO evidence, current selection, and lineage.
-
Treat ATS/model suggestions as review signals. Improve truthful wording, ordering, density, and supported terminology; do not invent evidence.
-
Run only the exact requested row:
make manual-pass-resumes JOB_IDS=<job-id> MANUAL_PASS_PROFILE=regular -
Confirm the stored
manualvariant derives from v2, includes governed YAML, HTML, PDF, ATS, evidence, validation, and model metadata, and leaves all non-target variants unchanged. -
Review
/resumes/<job-id>/variants; move an explicit selection only after human review. -
Render every PDF page to images and inspect legibility, clipping, overlap, wrapping, and semantic completeness. Recalculate ATS only through the explicit local action when needed.
Highlighting is separate and keeps its independent model/reasoning policy. A manual profile must never configure highlighting.
Output
Report the application only as authorized by the user, ATS movement, remaining unsupported/missing terms, artifact presence, lineage/selection invariants, visual-review outcome, and commands used. Do not modify applied status, notes, MRO evidence, or unrelated rows unless separately authorized.
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.
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.
- 2mo ago First seen · 54 lines · 64 tokens per session scan A 9f5808fbfb86
manual-resume-passthrough is a skill published in the GitHub repository mperkhou/career-agent-workbench (0 stars, last pushed 2mo ago), licensed MIT. It adds 64 tokens to every session and 539 once invoked, about $0.0003 per session on Opus 5.5. 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 skills, from other repositories
offer-toolkit-skill
A set of job-search tools covering the path from finding a vacancy to accepting an offer. It includes separate tools for job searches, job-description analysis, tailored resumes, behavioral interviews, offer comparisons, and salary negotiation.
job-hunt-skill
A workflow for finding and maintaining a searchable list of job openings from LinkedIn and public websites. It can use a résumé, career goals, example job descriptions, or existing links to build the list.
notion-knowledge-capture
Capture conversations and decisions into structured Notion pages; use when turning chats/notes into wiki entries, how-tos, decisions, or FAQs with proper linking.
apply
Help fill out a job application form. Generates personalized answers for every field using your profile and evaluation. Never auto-submits. Use when someone says 'help me apply', 'fill out this application', or 'application for'.
help
See all available career-ops skills, what they do, and which one to use next based on where you are in your job search. Use when someone says 'help', 'what can you do', 'how does this work', or seems unsure what to do next.
track
View and update your job application tracker. See all applications, filter by status, update progress, and get statistics on your search. Use when someone says 'show my applications', 'how is my job search going', 'update status', or 'tracker'.