Records agent workflows to create deterministic, zero-token replays and signed receipts that detect drift in agent-authored changes.
Also known as seldonframe/reelier
- Stars
- 3
- Tools
- —
- Downloads, 30 days
- —
- Latest version
- 0.24.0
- Last commit
- Aug 25, 2026
- License
- MIT
What is Reelier MCP?
Reelier records agent workflows to create deterministic, zero-token replays and signed receipts that detect drift in agent-authored changes.
Summary generated from the project's README
About Reelier MCP server
Reelier provides a system for recording agent workflows to create deterministic, zero-token replays and signed receipts. It is designed for solo developers, teams shipping agentic changes, and agencies that need verifiable proof of what an agent actually performed. By freezing a successful run as a replayable skill, users can re-execute the same logic without making new LLM calls, making the process significantly faster and cheaper than standard re-reasoning.
Developers can use the CLI to initialize inspections, compile traces into SKILL.md files, and run diffs to detect drift. The tool integrates with GitHub via an app to provide receipt comments on pull requests from bots like Dependabot. It can also be used as an agent plugin for Claude or Codex to teach models how to freeze repeatable tool-call jobs using the reelier-replay and reelier-write-safety skills. Setup involves the npm package and can be managed locally or via Docker.
What you can do with it
- 1Detect dependency driftA developer can gate Dependabot pull requests to ensure a dependency bump does not change the behavior of existing agent tool calls.
- 2Verify agent actionsAn agency can provide clients with signed, timestamped proof of exactly what an agent changed during a task.
Written from the project's README. Every use case is checked against a quote from it.
How to install Reelier MCP
Formats verified 10 Nov 2026Add to CursorAdd to GooseInstall Reelier MCP in Claude Code
$ claude mcp add reelier -- npx -y reelierInstall Reelier MCP in Cursor
~/.cursor/mcp.json
{
"mcpServers": {
"reelier": {
"command": "npx",
"args": [
"-y",
"reelier"
]
}
}
}Install Reelier MCP in VS Code
.vscode/mcp.json
{
"servers": {
"reelier": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"reelier"
]
}
}
}Install Reelier MCP in VS Code CLI
$ code --add-mcp '{"name":"reelier","type":"stdio","command":"npx","args":["-y","reelier"]}'Install Reelier MCP in Claude Desktop
claude_desktop_config.json
{
"mcpServers": {
"reelier": {
"command": "npx",
"args": [
"-y",
"reelier"
]
}
}
}Install Reelier MCP in Codex
$ codex mcp add reelier -- npx -y reelierInstall Reelier MCP in Codex config.toml
~/.codex/config.toml
[mcp_servers.reelier] command = "npx" args = ["-y", "reelier"]
Install Reelier MCP in Gemini CLI
$ gemini mcp add -s user reelier npx -- -y reelierInstall Reelier MCP in Gemini settings.json
~/.gemini/settings.json
{
"mcpServers": {
"reelier": {
"command": "npx",
"args": [
"-y",
"reelier"
]
}
}
}Automated checks
Ran Nov 14, 2026Full report →Passed our automated checks. That is not a security audit: read the code and give the server the narrowest access it needs. How checks work
- Source repository linked and reachableseldonframe/reelier is public and reachablegithub.com/seldonframe/reelier ↗Pass
- Package names this repository as its sourcereelier names seldonframe/reelier as sourcenpmjs.com/package/reelier ↗Pass
- Build provenance (Sigstore attestation)No build attestation published for this releaseNot checked
- Open source license (OSI)MITspdx.org/licenses/MIT.html ↗Pass
- Commit or release in the last yearLast commit or release 2026-08-25github.com/seldonframe/reelier ↗Pass
- OpenSSF ScorecardNot checked
- Package name not close to a popular packageNo popular package one edit away from reelierPass
- No critical advisory in the package or its dependencies99 resolved dependencies checked; no critical advisoryosv.dev ↗Pass
- No hidden instructions to the model0 tool descriptions and the README read; no override phrases, credential paths or hidden charactersPass
- Destructive tools are labelledNot checked
- Remote endpoint answers the MCP handshakeNot checked
README
View on GitHubReelier
Let your agents write. Keep the receipts.
Your agents worked all night. Here's exactly what changed.
Reelier records the run that worked, freezes it as a replayable skill, and replays it deterministically — every run comes back as a receipt: proof of what the agent did and what changed because of it. Agents make claims. Reelier writes receipts.
▶ watch with sound (27s)
Receipts on your agent PRs — install and done
Agent-authored PRs (Dependabot, Claude, Codex, Cursor, …) get a receipt comment in seconds: author, files changed, declared scope vs. what actually changed, sensitive paths flagged. No workflow file, no CLI, no config.
→ Install the Reelier receipts GitHub App — free on public repos, forever.
Reelier receipt — agent PR Author:
dependabot[bot]· Files changed: 2 (+119 −41) Declared scope: none (add.reelier/scope.ymlto enable unexpected-write detection) Sensitive paths touched: ⚠ 1 —package-lock.jsonProves scope and change, not correctness
A real receipt from Reelier's own repos — see one live. Declare scope per agent in .reelier/scope.yml (or a reelier-scope block in the PR body) and the receipt reports unexpected writes. The receipt proves scope and change, never correctness or safety.
Why
AI agents are non-deterministic — the same prompt, a different result every run — and they'll claim they did the work whether they did or not. Reelier records the run that worked, replays it deterministically, and writes a signed receipt that proves it. Point it at your existing CI in one workflow — it adds a verifiable receipt, it doesn't replace your stack.
Measured on a real head-to-head benchmark, same task, same data (full method):
- 1,000 / 1,000 replays byte-identical
- Every replay ships a signed receipt — proof of what ran and what changed, never a claim
- 0 LLM calls at replay — deterministic re-execution, not re-reasoning
Deterministic replay is also ~50× cheaper and ~59× faster than re-running the agent, on the same benchmark.
Install
npm i -g reelier && reelier init
# No Node install needed — same commands via Docker:
docker run --rm ghcr.io/seldonframe/reelier --help
reelier init [--dry-run] performs one checkpointed local inspection across all three Reelier paths: Path A observation coverage, Path B replay/freeze candidates, and Path C boundable/outcome-capable/shadow-only/unsupported connections and candidates. It does not deploy, gate, dispatch, upload, copy credentials, or rewrite host configuration. --dry-run writes nothing; the normal command writes only sanitized artifacts below .reelier/init/.
As an agent plugin
Teach your coding agent when to reach for Reelier. Same two commands, either host:
claude plugin marketplace add seldonframe/reelier
claude plugin install reelier@seldonframe
codex plugin marketplace add seldonframe/reelier
codex plugin add reelier@seldonframe
This installs two Agent Skills and nothing else. reelier-replay teaches your agent to freeze a
repeatable tool-call job and replay it at 0 tokens. reelier-write-safety covers bounding an
agent's writes before you grant them: what the recorder sees, what a policy refuses, and what a
receipt does and does not prove. It ships no MCP servers, so it does not wrap, observe, or gate
any tool call on its own; the reelier CLI does that, and the skills drive it via npx. Packaged in both the Agent Plugins v1.0.0 format (plugin/agent-plugins/) and the Claude Code format (plugin/claude/), generated from one source by scripts/build-plugin-packages.mjs.
Verified end to end on codex-cli 0.147.0-alpha.1.2: both formats install, enable, and the skill reaches the model. Other hosts are untested, and per-host status is tracked in docs/specs/agent-plugins-coverage-v1.md §4 rather than claimed here.
How to use it
reelier init --dry-run # inspect Path A/B/C locally; write nothing
reelier init # persist resumable sanitized inspection artifacts
reelier run <name>.skill.md # replay deterministically — 0 tokens (read-only by default)
reelier diff <name> # SAME or DRIFTED, per step — exit 1 on drift
reelier push <name>.skill.md # sync receipts to your ledger (opt-in)
reelier ci # write a workflow: drift-CI + PR receipts, one command
- Inspect, then record or freeze.
reelier initreveals observed coverage and local candidates without changing routes.reelier mcp --wrap "<mcp server>"proxies live tools;reelier scan/from-sessionfreezes supported history. - Compile.
reelier compileturns a trace into aSKILL.md— 0 LLM calls, minimal assertions, honest gaps printed as Open questions. - Replay.
reelier runreplays it at Level 0 — no LLM, byte-identical, read-only by default (writes need--allow-writes). - Diff.
reelier diffreports SAME or DRIFTED per step, with the failing assertion as the why — exit 1 on drift. - Log in.
reelier loginconnects this machine to Reelier Cloud with a device code in your browser — or setREELIER_CLOUD_URL/REELIER_CLOUD_KEYfor CI and self-hosting. - Push. Every run is a receipt;
reelier pushoptionally syncs it to a ledger for a permalink and an embeddable verified-replay badge.
Already have an Agent Skill? Convert it — your skill, minus the model:
reelier compile trace.jsonl --from-skill ./my-skill/SKILL.md
Three tests, one skill
| Test | Command | Answers |
|---|---|---|
| Determinism | reelier run <skill.md> |
Does this still do what it did? |
| Recovery | reelier run <skill.md> --fail N |
If this broke, would the skill notice and heal? |
| Drift | reelier run <skill.md> --wrap "<your mcp server>" |
Has the world moved out from under this skill? |
Taxonomy due to Mads Hansen's review of the launch post. Full semantics for each test, including recovery injection and manifest guardrails: docs/REFERENCE.md.
Gate Dependabot / Renovate bump PRs
Dependabot and Renovate open the PR and run your test suite — but neither knows what your agent actually does at runtime, so a dependency bump that silently changes a tool call's shape (a renamed field, a new default, a different error) sails through with green unit tests. This is the check they don't run.
Copy .github/workflows/reelier-bump-check.yml into your repo, point skill: at your own recorded .skill.md file(s), and it will: gate to PRs from dependabot[bot]/renovate[bot] (or a dependencies label), install the bumped dependency, replay your recorded skill live against it at --max-level 0 (0 tokens), and fail the check on the exact step that drifted.
This tests dependency and MCP-tool-call behavior — it does not test model upgrades; --max-level 0 never calls an LLM. Full listing copy and setup: docs/marketplace-listing.md.
Prove it
A pushed receipt carries a ladder of independently-verifiable claims — not one blanket "verified." Depending on what you turn on, it can be signed, timestamped, CI-attested, and carry cross-checkable provider request-ids. reelier verify recomputes every claim offline, and a claim you haven't enabled just renders as an honest gap, never a shamed one.
See a real one: reelier.com/r/HWBdmGob9KeHRqXi-OEaRD0z.
Full 8-rung ladder, what each rung does and doesn't prove: docs/REFERENCE.md.
If your skills are employees
| Employee lifecycle | Reelier equivalent |
|---|---|
| Skillify a session | reelier from-session |
| Performance review | reelier run + reelier diff |
| Fleet maintenance | scheduled replays + drift alerts |
| The record | signed receipts |
"Verified" describes the record, never the agent — a receipt proves what ran and what changed, not that the agent was good at its job.
An employment contract doesn't make an employee good — it makes what they did visible and bounded. Same here: receipts prove scope and change, never correctness.
Who it's for
- Solo dev / OSS maintainer — a real regression test again; drift can't pass silently.
- Team shipping agent changes — "it ran clean" becomes a checkable PR artifact, not a claim.
- Agency running agents for clients — signed, timestamped proof-of-delivery a client can verify.
- Marketplace buyer or seller — corroborated receipts are reviews that can't be astroturfed.
- Audit-facing ops — a signed, CI-attested trail of every write, idempotency key included.
MIT, free forever (versions ≤0.16.0 remain AGPL-3.0). Your data — skills, traces, runs — is specified in SPEC.md, so leaving is copying a folder.
Contributing: issues and PRs welcome — SPEC.md is the source of truth for formats; fix the code, not the spec. npm test before a PR.
If Reelier saved you a re-run, star it ⭐ — it's how other builders find it.
Reelier MCP questions
How do I add Reelier MCP to Claude Code?
Run claude mcp add reelier -- npx -y reelier in your terminal. Add --scope user to make it available in every project.
How do I add Reelier MCP to Cursor?
Open ~/.cursor/mcp.json and add the server under mcpServers, using the Cursor config shown in the install section above.
How does Reelier handle agent non-determinism?
Reelier records a successful run and replays it deterministically at 0 tokens, providing a signed receipt of exactly what changed without re-running the LLM.
Does Reelier replace my existing CI stack?
No, it is designed to be added to your existing CI as a verifiable receipt layer.
Is Reelier's replay process expensive?
No, deterministic replay is significantly cheaper and faster than re-running an agent because it uses 0 LLM calls.