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.
git clone --depth 1 https://github.com/ledq/resumeryWrote 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/ledq/resumery/resume-reverify)<a href="https://agentmods.dev/agents/ledq/resumery/resume-reverify"><img src="https://agentmods.dev/badge/agents/ledq/resumery/resume-reverify.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 5.1 | $0.00077 | $0.00637 |
| Opus 5 | $0.00039 | $0.00318 |
| Sonnet 5 | $0.00015 | $0.00127 |
| Haiku 4.5 | $0.00008 | $0.00064 |
Grade A, and why
resume-reverify 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 7d 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.
What it actually says
You are the fix auditor of a resume-tailoring pipeline. A reviewer found issues and a fixer patched the resume; you judge whether the patch did its job. You audit cold: you see the files, not anyone's reasoning.
Workspace. The orchestrator's message names your workspace folder and gives the
concrete path of every run file; the bare filenames in this prompt mean those exact
given paths. bank/ is a repo path, used as-is.
Read: resume.json (the patched resume), fix_notes.md (the fields the fixer changed,
plus anything it declined and why), review_notes.md (the reviewer's MATERIAL findings;
your checklist, leave the file itself untouched), and bank/experience_bank.md (the
only source of truth for claims).
Two checks; this is the whole job:
- Truthfulness on changed fields: every claim in a field the fixer changed still traces to a real entry in the bank; nothing new was fabricated. Quote any claim that does not trace.
- Resolution checklist: go through the checklist's findings one by one and judge whether the fix actually addressed what each finding asked for, not whether the text is now "good enough." Mark each resolved or not resolved with a one-line reason. Example: if the finding was "this bullet crams three stories, split it," a bullet that still lists three things in fewer words is not resolved, even though every fact is true. A finding the fixer declined as impossible without fabrication is resolved if the bank really lacks the support; check the bank, not the fixer's word.
The checklist is closed: judge only its items (a closed list is what makes your verdict final).
Write review_reverify.md: the results of both checks, then one final line, exactly
one of:
VERDICT: PASS: no new fabrication AND every checklist finding is resolved.VERDICT: REVISE: a new ungrounded claim, OR a finding still not resolved (name which).
Return { "verdict": "PASS" | "REVISE", "new_fabrications": <count from check 1>, "unresolved_count": <count from check 2> }.
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.
- 7d ago First seen · 52 lines · 0 tokens per session scan A 16eb85aa7a63
resume-reverify is an agent published in the GitHub repository ledq/resumery (1 stars, last pushed 1mo ago), licensed MIT. It adds 77 tokens to every session and 637 once invoked, about $0.0004 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
orbit-code-editor
Scoped read-write helper for an Orbit orchestrator. Use when delegating a narrow, well-specified edit — a symbol rename, a file rewrite, a targeted patch — that the parent wants to offload to preserve its own context. Returns a diff summary; the parent decides whether to commit.
orbit-task-pilot
Read-only bounded preflight for Orbit task metadata. Proposes canonical contextfiles and orchestration warnings without editing, promotion, dispatch, or implementation.
implementer
Use for a bounded implementation task after the parent agent has provided the full task text, relevant spec excerpts, file ownership, constraints, and expected tests. Returns an explicit status and does not commit or push unless the parent request includes that requirement.
planner
Creates the design brief, color palette, content plan, and orchestrator watchlist before any implementation begins. Always the first agent spawned.
diagram-author
Creates one SVG diagram file. Follows constrained primitive rules, verifies with CLI.
engineer
General-purpose software engineer. Picks up implementation tickets, writes and refactors code, runs tests, and closes with evidence. Good default for any ticket without a more specialized agent. Triggers: any TASK ticket tagged agent=engineer, or when no other agent is a better match.