resume-tailor-mirror Claude Code subagentA

resume-tailor-mirror from ymuromcev/ai-job-searcher is a Claude Code subagent: a helper Claude Code hands a task to, with its own instructions.

Install it, pinned
mdr add ymuromcev/ai-job-searcher/.claude/agents/resume-tailor-mirror.md@git:20260616.c8d48d0

Pins git:20260616.c8d48d0 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 14 of 14 checks passed
Kind
Claude Code subagent
Repository
ymuromcev/ai-job-searcher
Path
.claude/agents/resume-tailor-mirror.md
Versions recorded
5
Latest version
git:20260616.c8d48d0, committed Jun 16, 2026
First version recorded
May 25, 2026
Size
22,166 bytes
Repository stars
19
License
MIT

Strong-fit resume tailoring subagent — builds a tailored resume from scratch from the master profile + storybank with lexical JD mirror. Use this subagent when the orchestrator (engine/modules/tailor/tailor_orchestrator.js, invoked from prepare commit phase) needs ONE iteration of tailoring for a single Strong-fit job row. The orchestrator owns the outer loop and re-invokes this subagent with prev_resume_data + missing[] until the threshold or exit conditions are met (RFC 044 §"Loop semantics").

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# resume-tailor-mirror — Strong tailoring subagent (one iteration)

You are a single-iteration resume tailoring agent. You take a master profile + a JD and emit ONE tailored resume draft plus a JD-coverage table. **You do NOT loop internally.** The orchestrator outside owns iteration cap (6), threshold (85%), and no-growth detection. Your job is to produce the best possible single pass given the inputs you receive (including the previous iteration's draft + missing phrases, if any).

This is a Strong-fit-only path. Weak/Medium jobs go through the archetype-pick path (`pipeline-fit-evaluator`), not through you.

## Contract — input

The invoking code passes a single JSON object in the first user message. Schema:

```json
{
  "row_key": "ats:lever:plaid:pm-2026-05-24",
  "jd_text": "<full JD body, may be long>",
  "jd_structure": {
    "requirements": ["...", "..."],
    "responsibilities": ["...", "..."],
    "salary_text": "...",
    "location_text": "...",
    "full_text_excerpt": "..."
  },
  "master_profile_path": "profiles/jared/master_profile.md",
  "storybank_path": "profiles/jared/interview-coach-state/coaching_state.md",
  "profile_id": "jared",
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add ymuromcev/ai-job-searcher/.claude/agents/resume-tailor-mirror.md@sha256:515c6e5da6b78774

The line at the top of this page pins the label git:20260616.c8d48d0, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_tvv3dzffihezi7fa.svg)](https://markdownregistry.com/a/art_tvv3dzffihezi7fa)

1 badge image fetches in 30 days. What the badge shows.

Ask from your agent
claude mcp add --transport http markdownregistry https://markdownregistry.com/mcp/registry

Then ask it: what changed in ymuromcev/ai-job-searcher/.claude/agents/resume-tailor-mirror.md since the version I have? It reads every saved version here, no key and no account. Any agent that speaks MCP can add it.

Got a copy of resume-tailor-mirror.md from somewhere else? Ask it: where did my resume-tailor-mirror.md come from, and what was changed? It names the public original, the version yours is closest to and every changed line. The text is not kept.

Versions

The registry has recorded 5 versions of this file, between May 25, 2026 and Jun 16, 2026, about one every 5 days.

Watch this file (sign in, one email per new version)

versioncommittedcommitsizeaudit
git:20260616.c8d48d0 latest2026-06-16 c8d48d0 22,166 BA view · diff
git:20260528.07e2a362026-05-28 07e2a36 21,770 BA view · diff
git:20260526.8afc9782026-05-26 8afc978 19,858 BA view · diff
git:20260525.d03bc592026-05-25 d03bc59 18,232 BA view · diff
git:20260525.03691cf2026-05-25 03691cf 17,055 BA view
Check a whole project

From the root of your project, one line hashes each installed skill's SKILL.md, your AGENTS.md and your CLAUDE.md, and asks the registry once. Only the fingerprints and paths are sent.

sha256sum .claude/skills/*/SKILL.md AGENTS.md CLAUDE.md | curl -s --data-binary @- https://markdownregistry.com/api/v1/check-copies

In CI, add --fail-with-body: the answer is 409 when any file is behind, so the step fails and still prints which files.

sha256sum .claude/skills/*/SKILL.md AGENTS.md CLAUDE.md | curl -s --fail-with-body --data-binary @- https://markdownregistry.com/api/v1/check-copies

No sha256sum on your machine? shasum -a 256 prints the same lines.

Audit of the latest version

A  14 of 14 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Size between 200 bytes and 200 KB (22166 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

ymuromcev/ai-job-searcher · 19 stars · license MIT · pushed 2026-11-15 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_tvv3dzffihezi7fa
GET https://markdownregistry.com/api/v1/resolve?ref=ymuromcev/ai-job-searcher/.claude/agents/resume-tailor-mirror.md
GET https://markdownregistry.com/api/v1/blob/515c6e5da6b7877430e62b1c08595531dc64bea71729e6077de1c869f0155775

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: which agent file does what.

More from ymuromcev/ai-job-searcher

pipeline-fit-evaluator Claude Code subagent
ymuromcev/ai-job-searcher · .claude/agents/pipeline-fit-evaluator.md · Parallelizable wrapper for the Weak/Medium fit-evaluation flow defined in skills/job-pipeline/SKILL.md (Steps 4–8). Use…
git:20261109.231cc4b · audit A · 19 stars
CLAUDE.md CLAUDE.md file
ymuromcev/ai-job-searcher · CLAUDE.md
git:20260928.daa2920 · audit A · 19 stars
interview-coach SKILL.md skill
ymuromcev/ai-job-searcher · skills/interview-coach/SKILL.md · High-rigor interview coaching skill for job seekers. Use when someone wants structured prep, transcript analysis…
git:20260928.0eaf9a6 · audit A · 19 stars
job-pipeline SKILL.md skill
ymuromcev/ai-job-searcher · skills/job-pipeline/SKILL.md · Multi-profile job-search pipeline — scan ATS adapters, validate the pipeline, prepare Inbox jobs (fit scoring, CL gen…
git:20261115.d502a55 · audit A · 19 stars
onboard-profile SKILL.md skill
ymuromcev/ai-job-searcher · skills/onboard-profile/SKILL.md · Guide a new user through creating their first profile end-to-end: walk the questionnaire in chat, write…
git:20260616.56df549 · audit A · 19 stars
relokant-sweep SKILL.md skill
ymuromcev/ai-job-searcher · skills/relokant-sweep/SKILL.md · Repeatable sourcing sweep for the relokant sweet-zone channel — CIS-rooted, US-headquartered companies whose…
git:20260626.926d22f · audit A · 19 stars

Every file in ymuromcev/ai-job-searcher

Browse by kind, by grade A, or by owner.