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 | $0.00032 | $0.00269 |
| Sonnet 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 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 — 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.
- 10d 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 1mo ago), licensed MIT. It adds 64 tokens to every session and 539 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 2026-08-31.
Other skills, from other repositories
gws-gmail
Gmail: Send, read, and manage email.
recipe-block-focus-time
Create recurring focus time blocks on Google Calendar to protect deep work hours.
recipe-create-vacation-responder
Enable a Gmail out-of-office auto-reply with a custom message and date range.
recipe-save-email-attachments
Find Gmail messages with attachments and save them to a Google Drive folder.
happiness-skill
A Chinese-language guide to happiness based on reducing unmet wants, focusing on the present, and treating happiness as a trainable skill.
post-build-flow
Handles workflow verification and setup after build-workflow succeeds, or when the message contains workflow-verification-follow-up or workflow-setup-required. Load after direct builds, when verificationReadiness requires action, or on orchestrator verify/setup follow-up turns.