pipeline-fit-evaluator Claude Code subagentA
pipeline-fit-evaluator from ymuromcev/ai-job-searcher is a Claude Code subagent: a helper Claude Code hands a task to, with its own instructions.
mdr add ymuromcev/ai-job-searcher/.claude/agents/pipeline-fit-evaluator.md@git:20261109.231cc4bPins git:20261109.231cc4b 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/pipeline-fit-evaluator.md- Versions recorded
- 3
- Latest version
- git:20261109.231cc4b, committed Nov 9, 2026
- First version recorded
- May 25, 2026
- Size
- 16,713 bytes
- Repository stars
- 19
- License
- MIT
Parallelizable wrapper for the Weak/Medium fit-evaluation flow defined in skills/job-pipeline/SKILL.md (Steps 4–8). Use this subagent when the orchestrator (engine/commands/prepare.js runCommit batch-dispatch layer, per RFC 044) needs to evaluate one job row in parallel with others. ONE row per invocation; the orchestrator spawns N in parallel for a batch. Output schema matches what applyFitFields (engine/commands/prepare.js:1492) consumes today — this is a refactor, not a feature.
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
# pipeline-fit-evaluator — Per-row fit + CL subagent
You are a single-row job evaluation agent. The orchestrator (`tailor_orchestrator.js` invoked from `runCommit` per RFC 044) spawns one instance of you per non-Strong job row in a `prepare` batch, in parallel. Each instance does the full Step 4–8 flow from `skills/job-pipeline/SKILL.md` for **one** row and returns a JSON envelope. The orchestrator collects all envelopes and feeds them to `applyFitFields` + the existing artifact-generation path.
This subagent is **not** the Strong tailoring path. Strong rows go through `resume-tailor-mirror`. You handle Weak / Medium scoring + CL paragraph reuse — the existing archetype-pick logic, just parallelized.
## Contract — input
The invoking code passes a single JSON object in the first user message. Schema:
```json
{
"row_key": "ats:lever:acme:pm-2026-05-24",
"jd_text": "<full JD body>",
"jd_structure": {
"requirements": ["...", "..."],
"responsibilities": ["...", "..."],
"salary_text": "...",
"location_text": "...",
"full_text_excerpt": "..."
},
"profile_context": {
"profile_id": "jared",
"company": "Acme",
"title": "Senior PM, Growth",
…Read the whole file at its exact version.
How to install
mdr add ymuromcev/ai-job-searcher/.claude/agents/pipeline-fit-evaluator.md@sha256:9b8d6198140bcfcfThe line at the top of this page pins the label git:20261109.231cc4b, 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.
[](https://markdownregistry.com/a/art_ze57vn3ectlkpsi3)
1 badge image fetches in 30 days. What the badge shows.
claude mcp add --transport http markdownregistry https://markdownregistry.com/mcp/registry
Then ask it: what changed in ymuromcev/ai-job-searcher/.claude/agents/pipeline-fit-evaluator.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 pipeline-fit-evaluator.md from somewhere else? Ask it: where did my pipeline-fit-evaluator.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 3 versions of this file, between May 25, 2026 and Nov 9, 2026, about one every 84 days.
Watch this file (sign in, one email per new version)
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261109.231cc4b latest | 2026-11-09 | 231cc4b | 16,713 B | A | view · diff |
| git:20260616.e25aefe | 2026-06-16 | e25aefe | 16,501 B | A | view · diff |
| git:20260525.dc96e99 | 2026-05-25 | dc96e99 | 14,887 B | A | view |
Installed this file, say at pipeline-fit-evaluator.md? Drop it here to learn which saved version you have and what changed since. Your browser works out its SHA-256 fingerprint and sends only that; the file itself never leaves your computer.
Or paste its contents
Your agent can run this same check on the agent markdown files you have installed, up to 50 in one ask. Add the registry once:
claude mcp add --transport http markdownregistry https://markdownregistry.com/mcp/registry
Then ask it to check the files you have installed. No key and no account.
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
- pass: Size between 200 bytes and 200 KB (16713 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
ymuromcev/ai-job-searcher · 19 stars · license MIT · pushed 2026-11-15 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_ze57vn3ectlkpsi3 GET https://markdownregistry.com/api/v1/resolve?ref=ymuromcev/ai-job-searcher/.claude/agents/pipeline-fit-evaluator.md GET https://markdownregistry.com/api/v1/blob/9b8d6198140bcfcf171fa54473239fed569d005a6b9f123bd8c33f7e4ef8a4aa
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.