{"id":"cmuxjxwkc1emmad07g1yaaqof","slug":"agent-eval","publicId":"cfdd5ec9-13ce-47c4-8b0f-d077c8b0e3fc","name":"agent-eval","description":"Head-to-head comparison of coding agents (Claude Code, Aider, Codex, etc.) on custom tasks with pass rate, cost, time, and consistency metrics. Use when choosing between coding agents, or when a change to an agent setup needs measured pass rate, cost, and time rather than an impression.","version":"","author":"affaan-m","license":"MIT","compatibility":"","status":"completed","overallGrade":"B","scannerVersion":11,"fileCount":1,"hasSkillMd":true,"hasScripts":false,"hasReferences":false,"hasEvals":false,"hasAssets":false,"sourceType":"github","sourceUrl":"https://github.com/affaan-m/ecc/tree/main/skills/agent-eval","createdAt":"2026-10-07T03:32:38.295Z","completedAt":"2026-10-07T03:32:38.294Z","visibility":"public","publishedAt":"2026-08-06T17:11:19.298Z","category":"","frameworks":[],"badgeStatus":"conditional","downloadCount":0,"verdictRationale":{"summary":"Skill has warnings: 1 warning in security or structure checks.","verdict":"warn","scanners":[{"source":"vettd","weight":1,"verdict":"warn"},{"source":"cisco","weight":0.8,"verdict":"pass"}],"consensus":"warn","warnTriggers":["References external URL — review for indirect prompt injection risk"],"policyVersion":"consensus-v1","hardFailTriggers":[]},"verdictPolicyVersion":"consensus-v1","skillId":"cmshrvwtl04fzad07fpv1u2pb","findings":[{"id":"cmuxjxwkc1emnad07t7uhklh6","source":"vettd","category":"security","label":"References external URL — review for indirect prompt injection risk","detail":"External URL(s) detected in SKILL.md — referenced content can change after audit","severity":"medium","ruleId":"VTD-0088","owaspLlmCategory":null,"intent":null,"chainId":null,"fingerprint":"42638a8b7e9fc5df27449992eaebc724","filepath":"SKILL.md"}],"scannerRuns":[{"source":"cisco","status":"success","verdict":null,"grade":"A","findingCount":0,"criticalCount":0,"highCount":0},{"source":"vettd","status":"success","verdict":null,"grade":"B","findingCount":1,"criticalCount":0,"highCount":0}],"user":{"name":"Justin Pacella","image":"https://avatars.githubusercontent.com/u/97124458?v=4"},"repository":{"owner":"affaan-m","name":"ecc"},"freshness":{"status":"verified_unchanged","reason":null,"retryable":false,"renamedTo":null,"lastCheckedAt":"2026-10-21T22:41:01.893Z","lastVerifiedAt":"2026-10-21T22:41:01.893Z","lastChangeDetectedAt":"2026-08-14T15:10:28.683Z","scannedHash":"441ec6d618f25c67be2d2ee3a6498f15e10bd023","latestUpstreamHash":"441ec6d618f25c67be2d2ee3a6498f15e10bd023","nextCheckDueAt":"2026-10-23T00:35:36.819Z"},"signalCategories":[{"category":"safety","label":"Safety","form":"graded","verdict":null,"rows":[]},{"category":"reliability","label":"Reliability & Quality","form":"graded","verdict":null,"rows":[]},{"category":"performance","label":"Performance","form":"measured","verdict":{"form":"measured","magnitudes":[{"ruleId":"performance/static-context-tokens","label":"Static context tokens","value":1028,"unit":null,"method":"tiktoken/cl100k_base/skill-md-body"}]},"rows":[{"origin":"signal","id":"cmuxjxx9t1ervad07bg7nc62m","subjectType":"skill_audit","subjectId":"cmuxjxwkc1emmad07g1yaaqof","relatedType":"","relatedId":"","dataCategory":"performance","sourceClass":"scan","source":"vettd","ruleId":"performance/static-context-tokens","severity":null,"label":"Static context tokens","detail":null,"valueNum":1028,"valueText":null,"unit":null,"method":"tiktoken/cl100k_base/skill-md-body","derivation":null,"confidence":null,"sampleSize":null,"synthetic":false,"firstParty":true,"observedAt":"2026-10-07T03:32:33.000Z","payload":null},{"origin":"signal","id":"cmuxjy25x1fesad07nrn298xn","subjectType":"skill_audit","subjectId":"cmuxjxwkc1emmad07g1yaaqof","relatedType":"","relatedId":"","dataCategory":"performance","sourceClass":"scan","source":"vettd","ruleId":"performance/progressive-disclosure","severity":null,"label":"Progressive disclosure","detail":null,"valueNum":null,"valueText":"absent","unit":null,"method":null,"derivation":"read","confidence":null,"sampleSize":null,"synthetic":false,"firstParty":true,"observedAt":"2026-10-07T03:32:33.000Z","payload":null}]},{"category":"cost","label":"Cost","form":"measured","verdict":null,"rows":[]},{"category":"compatibility","label":"Compatibility","form":"unjudged","verdict":{"form":"unjudged"},"rows":[{"origin":"signal","id":"cmuxjxxi21etjad07uk4zu8mf","subjectType":"skill_audit","subjectId":"cmuxjxwkc1emmad07g1yaaqof","relatedType":"","relatedId":"","dataCategory":"compatibility","sourceClass":"scan","source":"vettd","ruleId":"compatibility/declared-environment-assumptions","severity":null,"label":"Declared environment assumptions","detail":null,"valueNum":null,"valueText":"","unit":null,"method":null,"derivation":"read","confidence":null,"sampleSize":null,"synthetic":false,"firstParty":true,"observedAt":"2026-10-07T03:32:33.000Z","payload":null},{"origin":"signal","id":"cmuxjxy1m1eyiad07wftl8ioz","subjectType":"skill_audit","subjectId":"cmuxjxwkc1emmad07g1yaaqof","relatedType":"declared_tool","relatedId":"Bash","dataCategory":"compatibility","sourceClass":"scan","source":"vettd","ruleId":"compatibility/declared-required-tools","severity":null,"label":"Declared required tool","detail":null,"valueNum":null,"valueText":"Bash","unit":null,"method":null,"derivation":"read","confidence":null,"sampleSize":null,"synthetic":false,"firstParty":true,"observedAt":"2026-10-07T03:32:33.000Z","payload":null},{"origin":"signal","id":"cmuxjxy9g1ezwad07rwglw0fu","subjectType":"skill_audit","subjectId":"cmuxjxwkc1emmad07g1yaaqof","relatedType":"declared_tool","relatedId":"Edit","dataCategory":"compatibility","sourceClass":"scan","source":"vettd","ruleId":"compatibility/declared-required-tools","severity":null,"label":"Declared required tool","detail":null,"valueNum":null,"valueText":"Edit","unit":null,"method":null,"derivation":"read","confidence":null,"sampleSize":null,"synthetic":false,"firstParty":true,"observedAt":"2026-10-07T03:32:33.000Z","payload":null},{"origin":"signal","id":"cmuxjxz791f43ad07tfgv6bc9","subjectType":"skill_audit","subjectId":"cmuxjxwkc1emmad07g1yaaqof","relatedType":"declared_tool","relatedId":"Read","dataCategory":"compatibility","sourceClass":"scan","source":"vettd","ruleId":"compatibility/declared-required-tools","severity":null,"label":"Declared required tool","detail":null,"valueNum":null,"valueText":"Read","unit":null,"method":null,"derivation":"read","confidence":null,"sampleSize":null,"synthetic":false,"firstParty":true,"observedAt":"2026-10-07T03:32:33.000Z","payload":null},{"origin":"signal","id":"cmuxjxyfd1f1cad07jm7iqgyi","subjectType":"skill_audit","subjectId":"cmuxjxwkc1emmad07g1yaaqof","relatedType":"declared_tool","relatedId":"Glob","dataCategory":"compatibility","sourceClass":"scan","source":"vettd","ruleId":"compatibility/declared-required-tools","severity":null,"label":"Declared required tool","detail":null,"valueNum":null,"valueText":"Glob","unit":null,"method":null,"derivation":"read","confidence":null,"sampleSize":null,"synthetic":false,"firstParty":true,"observedAt":"2026-10-07T03:32:33.000Z","payload":null},{"origin":"signal","id":"cmuxjxyl01f2pad07fl6b1iy0","subjectType":"skill_audit","subjectId":"cmuxjxwkc1emmad07g1yaaqof","relatedType":"declared_tool","relatedId":"Grep","dataCategory":"compatibility","sourceClass":"scan","source":"vettd","ruleId":"compatibility/declared-required-tools","severity":null,"label":"Declared required tool","detail":null,"valueNum":null,"valueText":"Grep","unit":null,"method":null,"derivation":"read","confidence":null,"sampleSize":null,"synthetic":false,"firstParty":true,"observedAt":"2026-10-07T03:32:33.000Z","payload":null},{"origin":"signal","id":"cmuxjxziq1f5ead07oja9qalj","subjectType":"skill_audit","subjectId":"cmuxjxwkc1emmad07g1yaaqof","relatedType":"declared_tool","relatedId":"Write","dataCategory":"compatibility","sourceClass":"scan","source":"vettd","ruleId":"compatibility/declared-required-tools","severity":null,"label":"Declared required tool","detail":null,"valueNum":null,"valueText":"Write","unit":null,"method":null,"derivation":"read","confidence":null,"sampleSize":null,"synthetic":false,"firstParty":true,"observedAt":"2026-10-07T03:32:33.000Z","payload":null},{"origin":"signal","id":"cmuxjy0ec1f97ad07e06hmni3","subjectType":"skill_audit","subjectId":"cmuxjxwkc1emmad07g1yaaqof","relatedType":"","relatedId":"","dataCategory":"compatibility","sourceClass":"scan","source":"vettd","ruleId":"compatibility/declared-name","severity":null,"label":"Declared skill name","detail":null,"valueNum":null,"valueText":"agent-eval","unit":null,"method":null,"derivation":"read","confidence":null,"sampleSize":null,"synthetic":false,"firstParty":true,"observedAt":"2026-10-07T03:32:33.000Z","payload":null}]},{"category":"sentiment","label":"Popularity","form":"unjudged","verdict":null,"rows":[]},{"category":"characteristics","label":"Characteristics","form":"unjudged","verdict":null,"rows":[]}],"signalCount":29,"publisherSupplied":["name","description","author","version","license"]}