mason benchmark report
mason has a benchmark score of 32/100 based on installability, startup reliability, MCP capability discovery, documentation quality, and safety signals.
Benchmark score
32
Docs score
0
Config score
0
Safety score
0
Benchmark status
| Install | unknown |
|---|---|
| Startup | unknown |
| Capability discovery | passed |
| Last tested | Sep 7, 2026 |
Installability
- npxconfidence: medium
npx -p mason-context mason-audit --dir . - npxconfidence: medium
npx -p mason-context mason-review --dir . --base origin/main - npxconfidence: medium
npx --package [email protected] mason-auto setup --host codex
Capabilities
tool
analyze_project
Run git history analysis on a codebase. Returns commit convention patterns, stale directories, and frequently changed files. These are aggregate stats across hundreds of commits that would be expensive to compute manually.
tool
export_to_confluence
Sync the project's concept map to Confluence as product-readable wiki pages: an index page, one page per feature (PM-language descriptions, no file paths), and a changelog page. Mason replaces managed page bodies; manual edits to those bodies are overwritten. Requires `mason_set_confluence` to have been called first.
tool
full_analysis
One-shot orientation for a project WITHOUT a concept map (get_snapshot returned exists:false). Returns git history stats, project structure with file counts, curated code sample previews (~60 lines each), and test-to-source mapping. On a mapped project, prefer get_snapshot — it is cheaper and answers feature/architecture questions directly.
tool
generate_snapshot_batch
Map step of the concept-map build. Returns one batch of source files (skeletons of every file in the batch plus a few deeper-read bodies for grounding), along with a system prompt instructing you to derive features and flows for ONLY this batch. Call repeatedly with the returned `nextOffset` until it is null, calling `save_partial_snapshot` between each call. Use product-natural feature names so partials merge cleanly in the reduce step.
tool
get_code_samples
Get previews (first ~60 lines) of representative source files from the codebase. Includes entry points, config files, hot files (frequently changed), test examples, and one file per directory for breadth. Read files natively for full content.
tool
get_context
Assemble task context: matching decisions with rationale, approval, owner, sources, last review, and freshness, plus related tests, file impact, and any available map entries. Proposals are suggestions; legacy records are unreviewed; accepted decisions are constraints subject to freshness. No initialization or map required. Pass task and optional files. map.status and diagnostics preserve missing or invalid knowledge. Impact covers up to three unique files, expanding directory anchors.
tool
get_impact
Trace the impact of changing files: historical co-change partners, references, and related tests. Deterministic, read-only, and usable without initialization, saved decisions, or a concept map.
tool
get_snapshot
Return the optional feature-to-file architecture map with drift and trust evidence. If no map exists, returns exists:false plus project structure, Git signals, and test pairs. Decision capture, get_context, and get_impact still work. No initialization required.
tool
mason_automation
Inspect installed automation and observed host events, or resume/check retained documentation repair evidence across sessions. status is read-only; check saves local baselines and verification reports without editing source or approving advisories. Returns concise results with a full report path. Works without a map.
tool
mason_check_drift
Check how far the concept map has drifted from HEAD. Deterministic (git + filesystem, no LLM). Returns which features/flows are stale and the changed files behind them, new source files not yet mapped, ghost files (mapped but deleted), renames, and a `recommendation`: `up-to-date` (nothing to do), `incremental` (update just the stale entries via save_snapshot), or `full-rebuild` (re-run the Map-Reduce build). Call this before trusting the map in a long session, or periodically to keep the map and any synced wikis fresh.
tool
mason_complete_init
Record completion of assistant instruction setup in .mason/project.json. Other tools work without this marker. Repeated calls preserve the original setup time and existing settings; pass confluenceConfigured only to change that setting.
tool
mason_init
Inspect this project now: returns documentation audit findings, committed-diff review findings, decision/map status, and a quickstart playbook. Quickstart and map modes are read-only and deterministic. Explicit mode: setup installs a pinned project runtime, MCP configuration, instructions and lifecycle hooks while retaining original audit evidence; use it only when the user requests setup. Optional host selects codex or claude. Optional base selects the review comparison; evidence imports CI manifests with check outcomes, commit freshness, and links to changed files and accepted decisions. mode: map returns the full Map-Reduce build workflow. Repeat calls refresh findings even after setup.
tool
mason_repair
Track documentation repairs against original audit evidence. prepare saves a local baseline and returns a scoped work order; verify reads that baseline and reports resolved, unresolved, review-required, unverified, and new findings. Suppressed advisories remain unresolved. Does not edit documentation or approve decisions. No map required.
tool
mason_set_confluence
Configure Confluence credentials. Two-step flow: (1) call without `spaceKey` to validate the credentials and receive a list of available spaces — relay them to the user. (2) call again with the same `baseUrl`/`email`/`apiToken` plus the chosen `spaceKey` to persist. Credentials are stored in `~/.mason/config.json`. Warn the user that the API token will be visible in chat history before they paste it.
tool
reduce_snapshot
Reduce step of the concept-map build. Returns every partial snapshot plus a system prompt asking you to merge them into one coherent project-wide map. Resolve platform variants into single product features, dedupe near-duplicates, and ensure no file is dropped. After producing the unified map, call `save_snapshot` to persist it (this also clears the partials).
tool
review_decision
Prepare a decision review: returns the full record and history, any operative accepted revision, provenance, changes and previews for both sets of anchors, and a reviewToken. Then record accept, reaffirm, or retire with that token, the authorized reviewer, and a reason. Acceptance replaces the operative revision; retirement withdraws the entire record including its proposal. Acceptance requires owner, source, readable Git HEAD, and committed anchor changes. Changed records or code invalidate the token. Identities and approvals are recorded assertions for normal PR review, not authenticated proof.
tool
save_decision
Capture or revise a decision proposal with rationale, anchors, optional owner, sources, and a known actor. No setup or map required. Writes a local record and preserves content history. Changes create a pending proposal while the last accepted revision remains operative; unchanged content does not re-verify or refresh it. Use review_decision for authorized acceptance or reaffirmation. A proposal cannot supersede a record with an operative accepted revision; review its replacement and retire the original separately.
tool
save_partial_snapshot
Persist the partial concept map you derived for one batch. Call this once per batch, with the `batchId` from the `generate_snapshot_batch` response. Partials accumulate in `.mason/partial-snapshots/` and are merged in the reduce step.
tool
save_snapshot
Save a concept-to-files map as a persistent project snapshot. Maps feature names and data flows to the files that implement them. Persists across conversations — future sessions can call get_snapshot to instantly find relevant files. No API key needed — you are the LLM generating the map.
tool
save_verification
Record verify_snapshot verdicts. Entries judged ok are stamped verifiedAt; failures are flagged verificationFailed with your note and surface in get_context, get_snapshot, and mason_check_drift until corrected. Verdict notes are required for failures.
Related pages
Frequently asked questions
What does the mason benchmark score include?
It combines install status, startup status, capability discovery, documentation score, configuration score, and safety score into a 0-100 benchmark_score.
Does MCP Server Finder call mason tools during discovery?
No. Capability discovery lists tools, resources, and prompts when possible, but does not invoke tools or read sensitive resources.
Why are some checks skipped?
Checks are skipped when they cannot be run safely without credentials, local configuration, or non-destructive execution guarantees.
Last updated