Reelier
About
Agents make claims. Reelier writes receipts — record an agent's tool-call workflow once, replay it deterministically at 0 tokens, and diff runs to catch drift.
Details
- Author
- Maxime Houle
- Downloads
- 2,323
- Categories
- Developer Tools, Automation
Jump to
- assert: status == 200
- assert: json.results is array
- assert: json.count >= 1 # numeric range
- assert: json.plan is string # type
- assert: json.id matches /^usr_/ # value pattern
Setting up with Highlight
This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:
- Download and install Highlight from highlightai.com/download
- Navigate to the plugins tab and select "Add Custom Plugin"
-
Configure the plugin with the settings below
Plugin Name
ReelierCommand (node, npx, python, etc.)Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
- Enable "Start Automatically" if you want the plugin to start when Highlight launches
From the repository
The README includes setup instructions such as docker run --rm ghcr.io/seldonframe/reelier --help.
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"reelier": {
"reelier": {
"command": "docker",
"args": [
"run",
"--rm",
"ghcr.io/seldonframe/reelier",
"--help"
]
}
}
}
}McpServers
{
"reelier": {
"command": "docker",
"args": [
"run",
"--rm",
"ghcr.io/seldonframe/reelier",
"--help"
]
}
}- Deterministic replay— Ask to replay a recorded skill withreelier runat zero tokens to verify it still works.
- Drift detection— Usereelier diffto compare a replay against the original and report SAME or DRIFTED per step.
- Skill compilation— Convert a trace or existing skill into a replayableSKILL.mdwithreelier compile.
- Local inspection— Runreelier init --dry-runto inspect observation coverage and replay candidates without writing anything.
- Receipt verification— Verify a pushed receipt offline withreelier verifyto recompute every claim.
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.
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 PRAuthor: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 areelier-scopeblock in the PR body) and the receipt reports unexpected writes. The receipt proves scope and change, never correctness or safety.
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.
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-runwrites nothing; the normal command writes only sanitized artifacts below.reelier/init/.
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-replayteaches your agent to freeze a repeatable tool-call job and replay it at 0 tokens.reelier-write-safetycovers 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; thereelierCLI does that, and the skills drive it vianpx. Packaged in both theAgent Pluginsv1.0.0 format (plugin/agent-plugins/) and the Claude Code format (plugin/claude/), generated from one source byscripts/build-plugin-packages.mjs.
Verified end to end oncodex-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 indocs/specs/agent-plugins-coverage-v1.md§4 rather than claimed here.
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 asOpen 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 thewhy— 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
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.
Dependabot and Renovate open the PR and run your test suite — but neither knows what your agent actuallydoesat 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.ymlinto your repo, pointskill:at your own recorded.skill.mdfile(s), and it will: gate to PRs fromdependabot[bot]/renovate[bot](or adependencieslabel), 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 doesnottest model upgrades;--max-level 0never calls an LLM. Full listing copy and setup:docs/marketplace-listing.md.
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 verifyrecomputes 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.
"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.
- 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 inSPEC.md, so leaving is copying a folder.
Contributing:issues and PRs welcome —SPEC.mdis the source of truth for formats; fix the code, not the spec.npm testbefore a PR.
If Reelier saved you a re-run,star it⭐ — it's how other builders find it.
This is a web browser that enables your coding agent, such as Claude Code, to visit websites on your behalf and assist you in identifying bugs or creating UI test cases.
fable-discipline is a Claude Code plugin that makes agentic software work follow repeatable working patterns: design before code, verify after edits, separate author from reviewer, preserve verified state between sessions, and report uncertainty honestly.
Preflight checks for paid x402 and MCP tools before marketplace listing.
An intelligent MCP server that automates the reproduction of GitHub issues for AWS CDK projects.
Modern Open source Test Management with MCP Server integration
Read-first Jenkins MCP server in Go for agent-driven build debugging. 20 tools including compare_builds, flaky-test detection, JUnit/Ginkgo failure parsing, and disk-cached console logs with on-disk path handoff. Write tools (trigger/stop/cancel) gated by JENKINS_MCP_READONLY env var.
Standardized testing harness for MCP servers and agent workflows
An MCP server for Nextflow development and testing, which requires a local clone of the Nextflow Git repository.
Provides a sleep/wait tool to add delays between operations, such as waiting between API calls or testing eventually consistent systems.
Pauses the execution of an agent for a specified duration.
Source-grounded launch review for x402, MCP, paid API, and agent-tool listings.
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
