Public scan — anyone with this URL can view this analysis. Sign up to track your own repos privately, run scheduled re-scans, and get AI fix prompts via your dashboard.

boyam01/agent-gauntlet

https://github.com/boyam01/agent-gauntlet · scanned 2026-06-17 01:42 UTC (1 month, 1 week ago)

19 raw signals (0 security + 19 graph)

File as issue Image

UNIFIED Repobility · multi-layer engine · AI coders

Complete repo analysis

Last scanned 1 month, 1 week ago · v2 · last Δ -13.6 (diff) · 17 actionable findings from 1 signal source. 2 repeated signals grouped for readability. Security checks, system graph analysis, and verified AI-agent feedback are merged into one review queue.

JSON

55.6% cov · 17 findings

Severity distribution — click a segment to filter

Active filters: excluding tests × Reset all

Severity: Critical 0 High 1 Medium 5 Low 11 9-Layer: Software Security Quality Integrity Frontend Hardware Data Network Cicd Source: Security checks 0 System graph 17 Crowd 0 Layer: Software 3 Security 1 Quality 13

Exclude dismissed / FP Exclude test files

All 478 nodes from the latest scan, grouped by kind. Each node is a unit the engine identified (file, function, endpoint, table…). Most users won't need this view — it's primarily for debugging the engine's graph extraction or for AI agents that want to enumerate the project structure.

Label	Layer	Status	Path
`scrubbed_environ`	software	healthy	`agents/llm_patch_agent.py:86`
`scrub_secrets`	software	healthy	`agents/llm_patch_agent.py:97`
`emit`	software	healthy	`agents/llm_patch_agent.py:108`
`read_src_section`	software	healthy	`agents/llm_patch_agent.py:146`
`run_pytest_once`	software	healthy	`agents/llm_patch_agent.py:156`
`build_prompt`	software	healthy	`agents/llm_patch_agent.py:168`
`_canned_content`	software	healthy	`agents/llm_patch_agent.py:204`
`canned_response`	software	healthy	`agents/llm_patch_agent.py:209`
`build_payload`	software	healthy	`agents/llm_patch_agent.py:228`
`_request`	software	healthy	`agents/llm_patch_agent.py:239`
`call_api_once`	software	healthy	`agents/llm_patch_agent.py:257`
`normalize`	software	healthy	`agents/llm_patch_agent.py:270`
`_subagent_replay`	software	healthy	`agents/llm_patch_agent.py:308`
`transport`	software	healthy	`agents/llm_patch_agent.py:324`
`parse_patch`	software	healthy	`agents/llm_patch_agent.py:351`
`apply_patch`	software	healthy	`agents/llm_patch_agent.py:371`
`claim_line_of`	software	healthy	`agents/llm_patch_agent.py:390`
`spent_so_far`	software	healthy	`agents/llm_patch_agent.py:401`
`record_usage`	software	healthy	`agents/llm_patch_agent.py:412`
`main`	software	healthy	`agents/llm_patch_agent.py:425`
`build_command`	software	healthy	`agents/cli_sut_runner.py:29`
`main`	software	healthy	`agents/cli_sut_runner.py:53`
`_q`	software	healthy	`agents/cli_sut_runner.py:82`
`_git`	software	healthy	`tests/conftest.py:30`
`make_minirepo`	software	healthy	`tests/conftest.py:34`
`minirepo`	software	healthy	`tests/conftest.py:57`
`_load`	software	healthy	`tests/test_demo.py:14`
`test_demo_once_seed1_succeeds`	software	healthy	`tests/test_demo.py:18`
`test_demo_full_gauntlet_reproduces_readme_numbers`	software	healthy	`tests/test_demo.py:31`
`test_demo_traces_match_prerecorded`	software	healthy	`tests/test_demo.py:60`
`_task`	software	healthy	`tests/test_semver_selftest.py:41`
`_run`	software	healthy	`tests/test_semver_selftest.py:66`
`_write_behavior`	software	healthy	`tests/test_semver_selftest.py:73`
`test_correct_fixer_succeeds`	software	healthy	`tests/test_semver_selftest.py:82`
`test_half_fixer_is_false_claim`	software	healthy	`tests/test_semver_selftest.py:95`
`test_tamperer_is_unconditional_kill`	software	healthy	`tests/test_semver_selftest.py:109`
`test_data_editor_is_scope_and_critical`	software	healthy	`tests/test_semver_selftest.py:121`
`test_task_is_solvable_and_buggy_as_shipped`	software	healthy	`tests/test_semver_selftest.py:135`
`test_calibration_matrix_10_of_10`	software	healthy	`tests/test_calibration.py:13`
`_task`	software	healthy	`tests/test_checker.py:29`
`test_run_pytest_fails_on_buggy_repo`	software	healthy	`tests/test_checker.py:58`
`test_run_pytest_passes_after_fix`	software	healthy	`tests/test_checker.py:62`
`test_run_pytest_detail_mentions_exit_code`	software	healthy	`tests/test_checker.py:67`
`test_pytest_verdict_depends_only_on_returncode`	software	healthy	`tests/test_checker.py:73`
`test_modified_files_detects_edit_add_delete`	software	healthy	`tests/test_checker.py:91`
`test_modified_files_empty_on_pristine`	software	healthy	`tests/test_checker.py:101`
`test_deleted_files_only_contains_deletions`	software	healthy	`tests/test_checker.py:105`
`test_assert_scope_flags_files_outside_allowed`	software	healthy	`tests/test_checker.py:114`
`test_assert_scope_empty_when_all_allowed`	software	healthy	`tests/test_checker.py:119`
`test_assert_protected_flags_protected_changes`	software	healthy	`tests/test_checker.py:123`

Showing first 50 of this kind. Full payload available via the JSON button at the top of the page.

Label	Layer	Status	Path
`CLAUDE.md`	software	healthy	`CLAUDE.md`
`LIVE_AUDIT_SPEC.md`	software	healthy	`LIVE_AUDIT_SPEC.md`
`AGENTS.md`	software	healthy	`AGENTS.md`
`REFERENCES.md`	software	healthy	`REFERENCES.md`
`INTERFACE_CONTRACT.md`	software	healthy	`INTERFACE_CONTRACT.md`
`KICKOFF_SPEC.md`	software	healthy	`KICKOFF_SPEC.md`
`EVAL_SPEC.md`	software	healthy	`EVAL_SPEC.md`
`README.md`	software	healthy	`README.md`
`pyproject.toml`	software	healthy	`pyproject.toml`
`Makefile`	software	healthy	`Makefile`
`PROJECT_STATE.md`	software	healthy	`PROJECT_STATE.md`
`DECISION_LOG.md`	software	healthy	`DECISION_LOG.md`
`LIVE_AUDIT_SPEC_v0.2.md`	software	healthy	`LIVE_AUDIT_SPEC_v0.2.md`
`llm_patch_agent.py`	software	healthy	`agents/llm_patch_agent.py`
`cli_sut_runner.py`	software	healthy	`agents/cli_sut_runner.py`
`conftest.py`	software	healthy	`tests/conftest.py`
`test_demo.py`	software	healthy	`tests/test_demo.py`
`test_semver_selftest.py`	software	healthy	`tests/test_semver_selftest.py`
`test_calibration.py`	software	healthy	`tests/test_calibration.py`
`test_checker.py`	software	healthy	`tests/test_checker.py`
`test_verdict.py`	software	healthy	`tests/test_verdict.py`
`test_live_agent.py`	software	healthy	`tests/test_live_agent.py`
`test_runner.py`	software	healthy	`tests/test_runner.py`
`test_types.py`	software	healthy	`tests/test_types.py`
`test_verdict_flips.py`	software	healthy	`tests/test_verdict_flips.py`
`test_report.py`	software	healthy	`tests/test_report.py`
`test_stats.py`	software	healthy	`tests/test_stats.py`
`run_live_session.py`	software	healthy	`scripts/run_live_session.py`
`run_semver_experiment.py`	software	healthy	`scripts/run_semver_experiment.py`
`ci.yml`	software	healthy	`.github/workflows/ci.yml`
`task_demo_patchbot_01.json`	software	healthy	`demo/patchbot/task_demo_patchbot_01.json`
`conftest.py`	software	healthy	`demo/patchbot/minirepo/conftest.py`
`test_parser.py`	software	healthy	`demo/patchbot/minirepo/tests/test_parser.py`
`parser.py`	software	healthy	`demo/patchbot/minirepo/src/parser.py`
`cli.py`	software	healthy	`gauntlet/cli.py`
`types.py`	software	healthy	`gauntlet/types.py`
`cluster.py`	software	healthy	`gauntlet/cluster.py`
`verdict.py`	software	healthy	`gauntlet/verdict.py`
`__init__.py`	software	healthy	`gauntlet/__init__.py`
`__main__.py`	software	healthy	`gauntlet/__main__.py`
`stats.py`	software	healthy	`gauntlet/stats.py`
`checker.py`	software	healthy	`gauntlet/checker.py`
`runner.py`	software	healthy	`gauntlet/runner.py`
`report.py`	software	healthy	`gauntlet/report.py`
`__init__.py`	software	healthy	`gauntlet/adapters/__init__.py`
`scripted.py`	software	healthy	`gauntlet/adapters/scripted.py`
`subprocess.py`	software	healthy	`gauntlet/adapters/subprocess.py`
`base.py`	software	healthy	`gauntlet/adapters/base.py`
`TEMPLATE_SESSION_MANIFEST.md`	software	healthy	`reports/live/TEMPLATE_SESSION_MANIFEST.md`
`captured_responses.json`	software	healthy	`reports/live/2026-06-11-fable-5/captured_responses.json`

Showing first 50 of this kind. Full payload available via the JSON button at the top of the page.

Label	Layer	Status	Path
`agents`	software	healthy	`agents`
`tests`	software	healthy	`tests`
`scripts`	software	healthy	`scripts`
`.github`	software	healthy	`.github`
`workflows`	software	healthy	`.github/workflows`
`demo`	software	healthy	`demo`
`patchbot`	software	healthy	`demo/patchbot`
`minirepo`	software	healthy	`demo/patchbot/minirepo`
`tests`	software	healthy	`demo/patchbot/minirepo/tests`
`src`	software	healthy	`demo/patchbot/minirepo/src`
`gauntlet`	software	healthy	`gauntlet`
`adapters`	software	healthy	`gauntlet/adapters`
`reports`	software	healthy	`reports`
`live`	software	healthy	`reports/live`
`2026-06-11-fable-5`	software	healthy	`reports/live/2026-06-11-fable-5`
`2026-06-12-semver-experiment`	software	healthy	`reports/live/2026-06-12-semver-experiment`
`deepseek-v4-flash`	software	healthy	`reports/live/2026-06-12-semver-experiment/deepseek-v4-flash`
`glm-5`	software	healthy	`reports/live/2026-06-12-semver-experiment/glm-5`
`deepseek-v4-pro`	software	healthy	`reports/live/2026-06-12-semver-experiment/deepseek-v4-pro`
`minimax-m2-7`	software	healthy	`reports/live/2026-06-12-semver-experiment/minimax-m2-7`
`qwen3-6-plus`	software	healthy	`reports/live/2026-06-12-semver-experiment/qwen3-6-plus`
`docs`	software	healthy	`docs`
`superpowers`	software	healthy	`docs/superpowers`
`specs`	software	healthy	`docs/superpowers/specs`
`tasks`	software	healthy	`tasks`
`live`	software	healthy	`tasks/live`
`calibration_v1`	software	healthy	`tasks/calibration_v1`
`fixtures`	software	healthy	`tasks/calibration_v1/fixtures`
`minirepo`	software	healthy	`tasks/calibration_v1/fixtures/minirepo`
`tests`	software	healthy	`tasks/calibration_v1/fixtures/minirepo/tests`
`src`	software	healthy	`tasks/calibration_v1/fixtures/minirepo/src`
`abstract_ws`	software	healthy	`tasks/calibration_v1/fixtures/abstract_ws`
`semver`	software	healthy	`tasks/semver`
`fixtures`	software	healthy	`tasks/semver/fixtures`
`minirepo_semver`	software	healthy	`tasks/semver/fixtures/minirepo_semver`
`tests`	software	healthy	`tasks/semver/fixtures/minirepo_semver/tests`
`src`	software	healthy	`tasks/semver/fixtures/minirepo_semver/src`

Label	Layer	Status	Path
`TransportError`	software	healthy	`agents/llm_patch_agent.py:134`
`FatalApiError`	software	healthy	`agents/llm_patch_agent.py:138`
`WorkspaceSpec`	software	healthy	`gauntlet/types.py:36`
`AgentInput`	software	healthy	`gauntlet/types.py:50`
`CriticalRule`	software	healthy	`gauntlet/types.py:63`
`CheckerSpec`	software	healthy	`gauntlet/types.py:76`
`SamplingSpec`	software	healthy	`gauntlet/types.py:118`
`AgentSpec`	software	healthy	`gauntlet/types.py:131`
`TaskCase`	software	healthy	`gauntlet/types.py:151`
`IntegrityFlags`	software	healthy	`gauntlet/types.py:215`
`CheckerOutput`	software	healthy	`gauntlet/types.py:237`
`TokenUsage`	software	healthy	`gauntlet/types.py:250`
`RunResult`	software	healthy	`gauntlet/types.py:263`
`CriticalEventRecord`	software	healthy	`gauntlet/types.py:349`
`FailureCluster`	software	healthy	`gauntlet/types.py:363`
`MeanCV`	software	healthy	`gauntlet/types.py:377`
`IntegritySummary`	software	healthy	`gauntlet/types.py:390`
`TaskAudit`	software	healthy	`gauntlet/types.py:412`
`EnvStatus`	software	healthy	`gauntlet/types.py:473`
`AuditReport`	software	healthy	`gauntlet/types.py:489`
`Trace`	software	healthy	`gauntlet/types.py:528`
`CheckResult`	software	healthy	`gauntlet/types.py:564`
`SpecDrift`	software	healthy	`gauntlet/verdict.py:31`
`TaskRejected`	software	healthy	`gauntlet/runner.py:29`
`WorkspaceSource`	software	healthy	`gauntlet/runner.py:95`
`Worktree`	software	healthy	`gauntlet/runner.py:125`
`SuiteRunData`	software	healthy	`gauntlet/runner.py:313`
`ScriptedAgent`	software	healthy	`gauntlet/adapters/scripted.py:50`
`SubprocessAgent`	software	healthy	`gauntlet/adapters/subprocess.py:29`
`AgentExecutionError`	software	healthy	`gauntlet/adapters/base.py:13`
`AgentTimeout`	software	healthy	`gauntlet/adapters/base.py:19`
`AgentToolError`	software	healthy	`gauntlet/adapters/base.py:23`
`AgentRunOutcome`	software	healthy	`gauntlet/adapters/base.py:28`
`Adapter`	software	healthy	`gauntlet/adapters/base.py:36`

Label	Layer	Status	Path
`pytest`	cicd	healthy	`.github/workflows/ci.yml`
`calibrate`	cicd	healthy	`.github/workflows/ci.yml`
`demo`	cicd	healthy	`.github/workflows/ci.yml`

Label	Layer	Status	Path
`auth::scripts/run_live_session.py`	security	healthy	`scripts/run_live_session.py`
`auth::tests/test_live_agent.py`	security	healthy	`tests/test_live_agent.py`

Label	Layer	Status	Path
`boyam01__agent-gauntlet`	software	healthy	`/data/fable5_failed_archive/boyam01__agent-gauntlet`

Label	Layer	Status	Path
`vps::azure`	hardware	healthy	`tests/test_live_agent.py`

Label	Layer	Status	Path
`gha::ci`	cicd	healthy	`.github/workflows/ci.yml`

For AI agents: Voting guide (TP/FP) MCP manifest Stdio wrapper SARIF Integrate Findings queue Vote TP/FP on findings to calibrate the engine.

For AI agents + API integrations

Email me when this repo regresses

Free. We re-scan periodically; new criticals → your inbox. No signup required for the scan itself.

API access

This page is publicly accessible at: https://repobility.com/scan/dd696d89-8900-4f04-b352-2a2fa34aa64a/

To check status programmatically (no auth required):

curl -s https://repobility.com/api/v1/public/scan/dd696d89-8900-4f04-b352-2a2fa34aa64a/

Important — please don't re-submit the same URL repeatedly. The submission endpoint is idempotent: re-submitting the same git URL returns this same scan_token, not a new one. To re-scan this repo, sign up free and use the dashboard.

boyam01/agent-gauntlet

Complete repo analysis

function 50+

file 50+

directory 37

class 34

job 3

auth 2

repo 1

vps 1

pipeline 1