All plugins

code-assurance-engine

Change-assurance engine: evaluates an immutable repository candidate against an explicit, reviewer-approved check contract and returns machine-readable evidence, findings and unverified gaps, so a green result has a defined scope. Disclosure — 6 tools plus a hermes assure CLI and an /assure slash command; assure_inspect reads the candidate repository read-only with git (minimal git environment, option-like base/head refs refused, repositories whose own git config defines filter drivers refused); the candidate is frozen and identified by content before the contract is agreed; assure_run is the only operation that executes repository code, and it refuses unless the assessment is APPROVED and its venue gates pass; state stays inside the plugin's data directory, including an explicit --state-dir given from /assure or hermes assure; the --owner-keys file is a path the caller supplies, so owner approval is only as strong as control of that path and of /assure; reports are private, local and render without external assets; no third-party network calls, no stored credentials, no telemetry and no self-updater.

Sahil-SS91Toolsv0.1.0Updated 5 days ago

About

Change-assurance engine: evaluates an immutable repository candidate against an explicit, reviewer-approved check contract and returns machine-readable evidence, findings and unverified gaps, so a green result has a defined scope. Disclosure — 6 tools plus a hermes assure CLI and an /assure slash command; assure_inspect reads the candidate repository read-only with git (minimal git environment, option-like base/head refs refused, repositories whose own git config defines filter drivers refused); the candidate is frozen and identified by content before the contract is agreed; assure_run is the only operation that executes repository code, and it refuses unless the assessment is APPROVED and its venue gates pass; state stays inside the plugin's data directory, including an explicit --state-dir given from /assure or hermes assure; the --owner-keys file is a path the caller supplies, so owner approval is only as strong as control of that path and of /assure; reports are private, local and render without external assets; no third-party network calls, no stored credentials, no telemetry and no self-updater.

Code Assurance Engine

Change assurance with receipts, not confidence scores.

Code Assurance Engine evaluates an immutable repository candidate against an explicit, reviewer-approved check contract. It returns machine-readable evidence, concrete findings and the gaps that remain unverified — so a green result has a defined scope.

Status: v0.1 evidence foundation. The read-only assessment, contract, evidence and reporting workflow is implemented and tested. Execution is a separate deployment track, enabled only after the trusted-host and native-containment prerequisites are approved.

At a glance

AreaWhat it gives you
Candidate evaluationOne immutable candidate, identified by content
Check contractReviewer-approved checks, expected evidence and failure conditions
EvidenceMachine-readable observations, findings and unverified gaps
VerdictsA bounded result that never collapses into an unconditional “safe”
PrivacyRead-only defaults, redaction and private local reports
AuthorityOwner-controlled approvals, separate from model output

Why it exists

A passing test suite answers a narrow question. It does not say what was checked, what was skipped, what the candidate actually did, or which claims remain unsupported.

Code Assurance makes those boundaries explicit:

  • the candidate is frozen and identifiable;
  • the checks are agreed before evaluation;
  • the evidence is recorded and re-verifiable;
  • missing proof is reported as missing, not rounded up to success.

How it works

  1. Freeze an immutable repository candidate and record its identity.
  2. Agree a reviewer-approved check contract covering commands, expected evidence and failure conditions.
  3. Assess the candidate through the public service and produce findings, observations and gaps.
  4. Reverify the recorded evidence and produce a private report.
  5. Extend to execution only when approved through the isolated, owner-controlled lane.

Verdicts

VerdictMeaning
ASSESSED_WITHIN_DECLARED_SCOPEThe declared checks completed and the evidence supports the stated scope
FINDINGS_PRESENTThe assessment found issues that need attention
INCOMPLETERequired evidence or scope is missing
INVALID_EVIDENCEThe evidence failed integrity or consistency checks

The engine never returns an unconditional SAFE, SECURE or READY_TO_MERGE. An empty findings list is not a safety claim.

Safety model

  • Read-only analysis is the default.
  • Candidate code execution is a separate, explicitly approved operation.
  • Public verification does not promote unauthenticated observations into proof.
  • Owner authority is external to the model and the candidate.
  • Model-supplied git revisions (base/head) are refused when they look like options (a leading -), resolved to a commit SHA behind --end-of-options, and only the SHA is forwarded to git. A revision can never be reinterpreted as a git flag such as --output=<path>.
  • git runs with a short environment allowlist (PATH, HOME, LANG, TMPDIR; SYSTEMROOT, TEMP, TMP on Windows) plus fixed overrides that switch off host and global git config. Provider API keys and anything else in the Hermes process never reach a git child.
  • A repository whose own git config (including any include.path file) defines a filter.* driver is refused before git status runs, because status would execute that driver. git status and the work-tree git diff never run inside submodule work trees, so changes inside a submodule are not listed (a moved submodule commit still is).
  • From /assure and hermes assure, --state-dir must sit inside the plugin's own data directory, the same rule the tools apply to state_dir. Anything else is refused before a file is written.
  • Reports are private by default and can be rendered without external assets.
  • Missing evidence stays visible in the output.

Owner trust root in gateway use

Owner approval (--owner-keys) is verified against a path the caller supplies, so owner authority is only as strong as control of that path and of access to /assure. In a gateway or multi-user deployment, treat the owner-keys path as a privilege boundary: pin it in trusted configuration, keep it outside any directory a model or chat participant can write, and do not let a request choose its own trust root.

What you can do today

  • Inspect a repository candidate and produce a proposed check contract.
  • Run the read-only assessment and status workflow.
  • Reverify evidence and generate a private report.
  • Integrate through the public service, CLI and native plugin surfaces.
  • Use the recorded verification harness to validate the evidence chain.

Roadmap

  • Complete the trusted-host and native-containment execution path.
  • Add the approved end-to-end owner-signed journey as a production lane.
  • Broaden check recipes and evidence adapters.
  • Publish stable compatibility and deployment guidance.

Documentation

Licensed under Apache-2.0. See NOTICE and THIRD_PARTY_NOTICES.md.

Repository: https://github.com/Sahil-SS9/code-assurance-engine

README from the reviewed commit 4a31218; it updates when the author re-pins.

More by Sahil-SS9

13 plugins by Sahil-SS9 in the catalog.

Sahil-SS9hermes-project-stewardshipDurable project ownership and bounded initiative management for Hermes fleets. Disclosure — a pre_llm_call hook adds a project's saved rules, decisions and facts to turns of bots assigned to that project; objective checks run allowlisted local programs only at autonomy level 3+ and GitHub objectives shell out to your own gh api; it creates and edits Hermes Kanban tasks through Hermes' internal kanban modules (title/body/tenant written directly to kanban.db), reads other Hermes profiles' project registries (projects.db, read-only, profile names and project counts only) to hint where existing projects live during onboarding, keeps its own SQLite DB under <Hermes home>/plugin-data/hermes-dockyard/, and its optional HTTP API (/stewardship/v1, 127.0.0.1) stays closed until you set a bearer token.Communityautomation85Sahil-SS9prompt-optimizerModel-aware prompt rewriting with quality scoring, analytics, and coaching. Disclosure — the default auto mode rewrites every user message of 5+ words through your configured model (one extra LLM call per turn) before the agent sees it.Communitytools34Sahil-SS9toolariaRescues oversized MCP and web tool results before they flood context.Communitytools22Sahil-SS9memlockReasserts pinned standing instructions after context compaction. Disclosure — scope=global pins apply to every session sharing the same HERMES_HOME; memlock_setup.py edits config.yaml and .claude/settings.json (with backups) only when you run it.Communitytools18

Developer Mode

Explore built-in Hermes toolsets and actions.

HermesAgent

Developer?

Create a Hermes extension for Desktop or agent workflows.

Developer Section