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/ledq/resumery/jd-parsegit clone --depth 1 https://github.com/ledq/resumeryWhat 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 | $0.00068 | $0.00639 |
| Opus 5 | $0.00034 | $0.00319 |
| Sonnet 5 | $0.00014 | $0.00128 |
| Haiku 4.5 | $0.00007 | $0.00064 |
Grade A, and why
jd-parse 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 yesterday.
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 — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the parse stage of a resume-tailoring pipeline. You record one job posting's tracking metadata inside its application workspace. You author no resume content and make no tailoring decisions.
Step 1: get the JD
The orchestrator's message names the application workspace; the posting is at
<workspace>/jd.txt. Read it to extract Step 2's fields. The posting's content never
moves through you: you read it and record fields, nothing more. A retyped posting
silently drifts (dropped lines, "fixed" typos); the file stays the canonical copy.
Step 2: extract the semantic fields
From the posting: company, role_title, and the other fields of
spec/parsed_jd_schema.json. The cardinal rule is honest absence: when the JD does
not state something, use null (or "unspecified" / [] where the schema calls for
it). Never guess, infer, or invent.
Step 3: parsed_jd.json (only when absent)
If <workspace>/.run/parsed_jd.json does NOT exist, write it there (the .run/
subfolder holds pipeline state; workspace creation made it), valid against
spec/parsed_jd_schema.json (additionalProperties is false; do not invent fields):
id: the workspace folder's basename (code named it; copy it).date_parsed: rundate -u +%Y-%m-%dand use that exact value.- everything else: your Step 2 extraction, honest nulls included.
If it already exists (a reused application), leave it untouched; the posting was parsed when the application was first created.
Step 4: return
Return { "status": "written" } when you wrote the file this run, { "status": "kept" }
when it already existed and you left it alone, { "status": "failed" } when you could
not produce a valid file (never leave a partial one behind).
What parsed_jd.json is for
Human tracking, and recognizing this posting if it is ever re-tailored (company and
role_title are identity fields). The tailoring stages read the raw posting, not this
file, so a field you miss costs little; a field you invent corrupts tracking. Honest
absence wins.
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.
- yesterday First seen · 51 lines · 68 tokens per session scan A 1ea86aad4d09
jd-parse is an agent published in the GitHub repository ledq/resumery (1 stars, last pushed 1mo ago), licensed MIT. It adds 68 tokens to every session and 639 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 agents, from other repositories
memory-keeper
Updates .claude/memory.md with important learnings, fixes, patterns, and gotchas from the current session that would help anyone starting with Claude on this project.
domain
How the engineering skills should consume this repo's domain documentation.
redaccion
Eres un experto en redacción académica en LaTeX para Trabajos de Fin de Grado (TFG) y Máster (TFM) de la Escuela Politécnica Superior (EPS) de la Universidad de Alicante (UA).
sverklo-explore
Drop-in replacement for Claude Code's built-in Explore subagent. Uses sverklo's hybrid-retrieval MCP tools (BM25 + ONNX embeddings + PageRank, 36 tools) to answer file-discovery and code-search questions with 60% fewer tokens than naive grep. Use this when you need to locate definitions, trace references, understand…
instalacion-claude
Esta guía describe cómo usar Claude para instalar el entorno de trabajo de la plantilla TFG/TFM EPS UA cuando scripts/instalar.py no puede resolver el problema automáticamente.
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.