Reelier

Snapshot tests and CI for agent workflows: record a run, replay it at 0 tokens, diff for drift.

Connector by seldonframe · GitHub account verified by the MCP Registry

IndexedMITLocal (stdio)★ 3

Install

Works with Claude Code, Codex, VS Code, Cursor, Windsurf, Claude Desktop. Read the repository before you give any tool access to your data.

npx agentmarket install connector/seldonframe-reelier

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

About

Snapshot tests and CI for agent workflows: record a run, replay it at 0 tokens, diff for drift.

Reviews

Write a review

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this server can do and what it asks for, from its tool list and install config. Checked Oct 25, 2026.

Tools: 7 read · 7 write · 0 delete · 5 not yet classified
Secrets: None asked for
Install scripts: Not scanned yet
Runs as: Node.js package

Tools by what they do 19

Read from the source code; the running server may list different tools.

Read 7 · Look things up without changing anything.

get_note
reelier_delegation_status
reelier_diff
reelier_jobs_search
reelier_outcome_status
reelier_scan
reelier_task_status

Write 7 · Create, change, send or run things.

add
create_note
reelier_outcome_invoke
reelier_push
reelier_replay
reelier_start_recording
reelier_stop_recording

Not yet classified 5 · We could not tell from the name and description.

reelier_artifact_stage
reelier_delegation_request
reelier_from_session
reelier_job_load
reelier_note

Files it touches

Any path the agent passes to its tools

Tools (19)

Read from the source code; the running server may differ. Descriptions are the server’s own words; hidden characters are shown as [U+…].

add
Adds two numbers and returns {result}.
create_note
Creates a note and returns {id, text}. A fresh random id every call.
get_note
Fetches a note by id and returns {id, text, found}.
reelier_artifact_stage
Stage text for a reviewed outcome; returns an opaque commitment only.
reelier_delegation_request
Request a narrower child authority from the authenticated parent task and allocation. Fan-out is computed by the Authority Cell.
reelier_delegation_status
Read the redacted state of a child delegation.
reelier_diff
Compare two runs of the same skill and report SAME or DRIFTED — the drift-detector for a recorded baseline replayed on a schedule. Compares per-step outcomes, structure, and heal-level from .reelier/runs/<skill>.jsonl (defaults to the last two runs); data values that legitimately change run-to-run are NOT drift. Drifted steps carry why (the failing assertion). To check a MODEL upgrade: re-record the workflow with the new model, then diff against your frozen baseline — replaying a pinned skill can't reveal model changes (replay never calls a model). Honest when there aren't two runs yet.
reelier_from_session
Compile a SKILL.md from a session transcript. USE WHEN: the work ALREADY happened (this session or by hand) — recording can't be retroactive. NOT for work that hasn't happened yet (record that live via the reelier mcp proxy). Get the transcriptPath from reelier_scan first. Returns the written skill's path, stats, and open questions — or, honestly, that nothing in the transcript was replayable. If the workflow used a relative time window ("this week"), bind it to a date variable (e.g. {{today-7d}}) so later replays pull the CURRENT window, not a frozen one — the openQuestions output flags this.
reelier_job_load
Load one deployed job and its bounded Outcome.
reelier_jobs_search
Find deployed jobs without loading every Outcome schema.
reelier_note
Narrate what you're about to do, in one sentence (e.g. "I'm about to pull this week's bookings"). No-op if not currently recording.
reelier_outcome_invoke
Invoke a loaded bounded Outcome on hosts without dynamic tool lists.
reelier_outcome_status
Read the redacted lifecycle of a governed outcome.
reelier_push
Push a skill's local run records (and, on first push, the skill file) to your receipt ledger, where each receipt gets a shareable permalink + verified-replay badge. Requires an apiKey — from `reelier login` (or REELIER_CLOUD_KEY in env) — reports skipped-no-key honestly when absent; the cloud URL always resolves on its own. USE WHEN: a run's receipt should be durable or shareable.
reelier_replay
Run a skill file at Level 0 (deterministic replay, zero LLM calls) and return the real run record: per-step outcomes, timing, totals, and — when a step drifted — why (the failing assertion). Never fabricates a pass. Reproduces the recorded TOOL CALLS (MCP/HTTP) only — no LLM reasoning or prose step re-runs. It does NOT schedule itself: pair with cron/CI for recurring runs. Pass vars to fill {{templated}} inputs (e.g. a computed date window) so a replay pulls current data. READ-ONLY by default: 'idempotent-write' steps are held back (reported as a refused/failed step) unless you pass allowWrite…

Show 4 more tools

reelier_scan
Discover replayable workflows in an agent's session history (defaults to ~/.claude/projects). Returns each session's transcript path — feed one to reelier_from_session. Only MCP/HTTP tool-call sequences are replayable; native file/shell actions are reported as skipped, never fabricated into a fake result. USE WHEN: deciding which past work is worth compiling into a replayable skill.
reelier_start_recording
Begin recording the tool calls you're ABOUT to make as a Reelier trace — it captures only calls made after this, so you cannot record work retroactively. If the workflow already happened earlier this session, do NOT re-do it just to record it — compile it straight from history instead (reelier_from_session, or the `reelier serve` scan→from_session path). Otherwise: call reelier_note before each logical step to narrate intent, then call the tools you'd normally call — they pass through unchanged and are logged. Call reelier_stop_recording when done.
reelier_stop_recording
Stop the current recording and return the trace file path + how many calls were logged.
reelier_task_status
Read the redacted authority graph for a task.

Signals

Stars: 3
Forks: 1
Open issues: 9
Last commit: Aug 20, 2026 (2 months ago)
Last release: Aug 1, 2026 (2 months ago)

From GitHub (fetched Oct 24, 2026).

Details

Registry name: io.github.seldonframe/reelier
Version: 0.24.0
Auth: No auth
Packages: npm reelier
License: MIT
Repository: github.com/seldonframe/reelier
Website: www.reelier.com
First seen: Oct 24, 2026
Last checked: Oct 24, 2026
Source: Official MCP Registry github-graphql