developer-tools Static interface comparison

viberank

1.1.0 1.2.0

FAILPending human review

1 new unknown capability requires explicit review.

View the upgrade review as Markdown

A shareable summary of this comparison for an issue, pull request or ticket. Select the text and copy it.

Tools4 → 5
Added1
Removed0
Schema changes4
Input schema changes4
Output schema changes0
Unclassified schema changes0
Description changes4
New write authority0
New destructive authority0
New unknown authority1
AnalysisFAIL

INTERFACE DIFF

What changed, tool by tool

Classification from the recorded findings · definitions from the published snapshots

5 tools with recorded changes

  1. get_leaderboardModifiedSchemaDescriptionREVIEWINFO

    What changed

    • get_leaderboard — Schema change: input property added: tool.
    • get_leaderboard — Input type change: property limit changed: description "Number of top user… → "How many top entri…, +maximum=50, +minimum=1, type "number" → "integer".
    • get_leaderboard: description changed.

    Why it could matter

    • Calls or consumers built for the earlier schema may need to change.
    • Arguments of the old type may no longer validate against the new schema.
    • Models choose and call tools partly from their descriptions.

    What to verify

    • Validate representative existing tool calls against the new argument schema.
    • Spot-check that agents still select this tool as intended.
    Declared effect
    unknown → unknown
    Description
    PreviousGet current Viberank leaderboard rankings
    CurrentThe current viberank leaderboard, ranked by API-equivalent cost. Each entry has rank, username, totalCost (USD), totalTokens, tools, verified, underReview and profileUrl. Pass tool to rank only the users of one tool; get_stats lists the tool slugs.

    Input schema

    PropertyPrevious (1.1.0)Current (1.2.0)Change
    limitnumber, default=10optionalinteger, default=10, maximum=50, minimum=1optional
    • Description changed
    • Constraint: maximum
    • Constraint: minimum
    • Type changed

    maximum: — → 50

    minimum: — → 1

    type: "number" → "integer"

    toolnot presentstringoptional
    • Added
    1 unchanged entry
    • (schema root)

    No output schema is recorded for this tool in either release.

    Exact JSON from the published snapshots

    Loads the exact recorded definitions of this tool from both releases. The full snapshots are linked under Evidence and provenance.

    Link to this tool
  2. get_profileModifiedSchemaDescriptionREVIEWINFO

    What changed

    • get_profile — Schema change: input property username changed: description "GitHub username to… → "The GitHub usernam….
    • get_profile: description changed.

    Why it could matter

    • Calls or consumers built for the earlier schema may need to change.
    • Models choose and call tools partly from their descriptions.

    What to verify

    • Validate representative existing tool calls against the new argument schema.
    • Spot-check that agents still select this tool as intended.
    Declared effect
    unknown → unknown
    Description
    PreviousGet Viberank profile for a specific user
    CurrentOne developer's viberank profile: global rank, total cost and tokens, days tracked, tools and whether it is verified. Profiles are keyed by GitHub username. Returns found: false when there's no such profile.

    Input schema

    PropertyPrevious (1.1.0)Current (1.2.0)Change
    usernamestringrequiredstringrequired
    • Description changed
    1 unchanged entry
    • (schema root)

    No output schema is recorded for this tool in either release.

    Exact JSON from the published snapshots

    Loads the exact recorded definitions of this tool from both releases. The full snapshots are linked under Evidence and provenance.

    Link to this tool
  3. get_statsAddedAuthorityFAIL

    What changed

    • New tool get_stats, declared with unknown effect.

    Why it could matter

    • Valyd could not determine this tool’s effect from its declared interface, so its authority is not known.

    What to verify

    • Read the tool’s documentation and schema before allowing agents to use it.
    Declared effect
    — → unknown

    Input schema

    PropertyPrevious (1.1.0)Current (1.2.0)Change
    (schema root)not presentobject
    • Added

    No output schema is recorded for this tool in either release.

    Exact JSON from the published snapshots

    Loads the exact recorded definitions of this tool from both releases. The full snapshots are linked under Evidence and provenance.

    Link to this tool
  4. get_usageModifiedSchemaDescriptionREVIEWINFO

    What changed

    • get_usage — Schema change: input property force_refresh changed: description "Force refresh the … → "Re-run ccusage ins….
    • get_usage: description changed.

    Why it could matter

    • Calls or consumers built for the earlier schema may need to change.
    • Models choose and call tools partly from their descriptions.

    What to verify

    • Validate representative existing tool calls against the new argument schema.
    • Spot-check that agents still select this tool as intended.
    Declared effect
    unknown → unknown
    Description
    PreviousGet current Claude Code usage statistics from ccusage
    CurrentRead the user's local AI coding usage (Claude Code, Codex, Gemini CLI, OpenCode and the other tools ccusage supports) by running ccusage@20 on this machine. Returns a summary: API-equivalent cost in USD, tokens, days tracked, date range and cost per tool. Sends nothing anywhere. Can take a minute on a long history; results are cached for 5 minutes.

    Input schema

    PropertyPrevious (1.1.0)Current (1.2.0)Change
    force_refreshboolean, default=falseoptionalboolean, default=falseoptional
    • Description changed
    1 unchanged entry
    • (schema root)

    No output schema is recorded for this tool in either release.

    Exact JSON from the published snapshots

    Loads the exact recorded definitions of this tool from both releases. The full snapshots are linked under Evidence and provenance.

    Link to this tool
  5. submit_to_viberankModifiedSchemaDescriptionREVIEWINFO

    What changed

    • submit_to_viberank — Schema change: input property removed: auto_detect_username.
    • submit_to_viberank — Schema change: input property github_username changed: description "GitHub username fo… → "The user's own Git….
    • submit_to_viberank: description changed.

    Why it could matter

    • Calls or consumers built for the earlier schema may need to change.
    • Models choose and call tools partly from their descriptions.

    What to verify

    • Validate representative existing tool calls against the new argument schema.
    • Spot-check that agents still select this tool as intended.
    Declared effect
    unknown → unknown
    Description
    PreviousSubmit Claude Code usage statistics to Viberank leaderboard
    CurrentUpload the user's local usage to the public viberank.app leaderboard. Call it only when the user asked to submit. With a VIBERANK_TOKEN configured, the submission is verified and filed under the token's account, so leave github_username out. Without a token, github_username is required and must be the user's own GitHub handle, confirmed with them, because it becomes a public profile. Called without one, it uploads nothing and suggests a handle to confirm with the user before calling again. On success it returns rank, tier and a README badge you can offer to add.

    Input schema

    PropertyPrevious (1.1.0)Current (1.2.0)Change
    auto_detect_usernameboolean, default=trueoptionalnot present
    • Removed
    github_usernamestringoptionalstringoptional
    • Description changed
    1 unchanged entry
    • (schema root)

    No output schema is recorded for this tool in either release.

    Exact JSON from the published snapshots

    Loads the exact recorded definitions of this tool from both releases. The full snapshots are linked under Evidence and provenance.

    Link to this tool

Evidence and provenance

Static findings
FAIL from Modelara’s automated analysis of the two declared interfaces. A policy outcome, not a security rating or a runtime test.
Human review
Pending human review. No reviewer decision is recorded for this comparison.
Published evidence
Part of Valyd’s published data generation listed in valyd-data-source.json. Published records are not rewritten.
Show provenance and exact files
Comparison
sculptdotfun-viberank/1.1.0~1.2.0The published comparison identifier.
Analyzer
modelara v0.1.8Policy version not recorded.Analyzed Nov 17, 2026, 12:37 AM UTC.
Distribution
npm
Previous release
viberank-mcp@1.1.04 tools · published by the registry Sep 23, 2026, 2:08 PM UTCArtifact integritysha512-AU0pldYLVMNYik1ZNy0IPkM0/y4cYFArRSMNxaqXV/FU4iI3Ui4ce1ouZSeHongUr/emek93eAJ925Ei/7dxMw==Interface fingerprintsha256:bcfd0dedfe504074221eb9f7cafa5849542bc8d2eadbdfe5915cb49b3baa5ceaExact interface snapshot (JSON)
Current release
viberank-mcp@1.2.05 tools · published by the registry Oct 26, 2026, 10:34 AM UTCArtifact integritysha512-5RPCmOY9h5WBSMvruYK8wP+RveRkpXF4gTVuxekYjeTm0mI1VciLmiBQxCzWxqzj9fBns3CgTYPgudf5H0YSgg==Interface fingerprintsha256:7db9b6f50bd880bb9b639a4694d9faea8a2c4bd5faa9bff1654101a30d4e11bbExact interface snapshot (JSON)

The integrity value or digest identifies the exact artifact that was inspected; it does not show that the package is safe. The interface fingerprint identifies the declared tools and schemas Modelara recorded for that release.

MODELARA ANALYSIS OUTPUT

Interface findings

Analyzed with Modelara v0.1.8 · Nov 17, 2026

Policy failures

1 finding
  • get_statsFAILAdded

    New capability with unknown effect; the effect is unknown, so Modelara cannot establish that it is read-only

    Authority
    —UNKNOWN

Requires review

4 findings
  • get_leaderboardREVIEWChanged

    Input schema changed

    Show details
    • input property added: tool
    • input property limit changed: description "Number of top user… → "How many top entri…, +maximum=50, +minimum=1, type "number" → "integer"
    Authority
    UNKNOWNUNKNOWN
    Authority unchanged
  • get_profileREVIEWChanged

    Input schema changed

    Show details
    • input property username changed: description "GitHub username to… → "The GitHub usernam…
    Authority
    UNKNOWNUNKNOWN
    Authority unchanged
  • get_usageREVIEWChanged

    Input schema changed

    Show details
    • input property force_refresh changed: description "Force refresh the … → "Re-run ccusage ins…
    Authority
    UNKNOWNUNKNOWN
    Authority unchanged
  • submit_to_viberankREVIEWChanged

    Input schema changed

    Show details
    • input property removed: auto_detect_username
    • input property github_username changed: description "GitHub username fo… → "The user's own Git…
    Authority
    UNKNOWNUNKNOWN
    Authority unchanged

Informational

4 findings
  • get_leaderboardINFOChanged

    Description changed

    Authority
    UNKNOWNUNKNOWN
    Authority unchanged
  • get_profileINFOChanged

    Description changed

    Authority
    UNKNOWNUNKNOWN
    Authority unchanged
  • get_usageINFOChanged

    Description changed

    Authority
    UNKNOWNUNKNOWN
    Authority unchanged
  • submit_to_viberankINFOChanged

    Description changed

    Authority
    UNKNOWNUNKNOWN
    Authority unchanged
What do these results mean?
PASS
No policy-significant interface change detected.
REVIEW
Interface changes require inspection.
FAIL
A policy-significant change was detected.
INVALID
The comparison could not be evaluated reliably.
← Back to viberank release history