synapsor-protect

A command that drafts one disabled Synapsor Safe Action for an existing application. A Safe Action is a defined business data operation that is prepared for human review but is not allowed to run.

In plain words
What is it for?
Use it to describe one intended business action, inspect the application's documented schema and reviewed Runner configuration, and generate the corresponding disabled action file. It does not activate, approve, apply, commit, or undo data changes.
Why use it?
It helps translate a requested data operation into a reviewable definition without granting permission to change data or silently deciding what the operation may access.

Command

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add commands/synapsor/synapsor-runner/synapsor-protect
Clone the repo
git clone --depth 1 https://github.com/Synapsor/Synapsor-Runner
Per session 21 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 528 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00021 $0.00528
Opus 5 $0.00010 $0.00264
Sonnet 5 $0.00004 $0.00106
Haiku 4.5 $0.00002 $0.00053

Measured 2d ago against content hash fa96e39f83a1, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

synapsor-protect scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

plugins/cursor/synapsor/commands/synapsor-protect.md · 46 lines

What it actually says

Protect one application data action

Turn the developer's requested business action into one disabled, deterministic Synapsor Safe Action. This command drafts authority for human review; it never activates an action or approves, applies, commits, or reverts source data.

  1. Ask for the action name and one-sentence intended business effect if they are not already explicit. Work on one action only.

  2. Confirm that synapsor.runner.json exists. If it does not, stop and direct the developer to the Runner own-database onboarding. Do not invent source, tenant, principal, credential, or writeback authority.

  3. Inspect project schema/ORM/OpenAPI/test files and the reviewed Runner config. Never print environment-variable values, connect to an unapproved database, execute project code for discovery, or treat names as security authority.

  4. Run the pinned Runner scaffold with a shell-safe action identifier and the developer's exact intent:

    npx -y @synapsor/[email protected] start --action <action_name> --description "<reviewed intent>"

  5. Read synapsor/SAFE_ACTION_AGENT.md and follow it as the canonical safety instruction source. Edit only the generated file under synapsor/actions/. Keep the action concise and preserve every unresolved authority question until the developer supplies a reviewed answer.

  6. Run the project formatter for the action file, then run:

    npx -y @synapsor/[email protected] action validate <generated-action.ts> --json

  7. Fix deterministic diagnostics without weakening tenant/principal scope, visibility, bounds, conflict handling, approval, or executor authority.

  8. Report the disabled draft digest, exact generated tests, pending live tests, and unresolved authority. Do not claim the action is active.

  9. Tell the developer to open the secured localhost Workbench personally, run the non-mutating staging preview, review the exact Data PR and digest, and activate it there. There is intentionally no action activate CLI or MCP tool.

Never modify .synapsor/active, the active contract reference, Cursor MCP configuration, runtime credentials, approval identity, or source data. Never add raw SQL, generic database tools, model-visible approval/apply tools, or a command that bypasses the Workbench confirmation.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 46 lines · 21 tokens per session scan A fa96e39f83a1

Subscribe to this mod's changes

synapsor-protect is a command published in the GitHub repository Synapsor/Synapsor-Runner (2 stars, last pushed 5d ago), licensed Apache-2.0. It adds 21 tokens to every session and 528 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.