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.
Sign up free Scan another repo

SahilAshar/llm-token-harness

https://github.com/SahilAshar/llm-token-harness · scanned 2026-06-15 23:59 UTC (2 months, 3 weeks ago)

23 raw signals (0 security + 23 graph)

File as issue Image
UNIFIED Repobility · multi-layer engine · AI coders

Complete repo analysis

Last scanned 2 months, 3 weeks ago · v1 · 21 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
Combined
82.9
/100
Security checks
83
0 findings
System graph
83
66.7% cov · 21 findings
Critical
0
click to filter
Agents
10
0 votes
Crowd
0
reported
Severity distribution — click a segment to filter
Active filters: excluding tests × Reset all
Severity: Critical 0 High 0 Medium 4 Low 10 9-Layer: Software Security Quality Integrity Frontend Hardware Data Network Cicd Source: Security checks 0 System graph 21 Crowd 0 Layer: Software 1 Frontend 1 Security 2 Cicd 1 Quality 16

All 334 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.

LabelLayerStatusPath
tasks software healthy tests/test_dataset.py:33
test_loads_25_tasks software healthy tests/test_dataset.py:37
test_expected_tools_are_real_tools software healthy tests/test_dataset.py:41
test_tool_distribution software healthy tests/test_dataset.py:55
test_parallel_tasks software healthy tests/test_dataset.py:62
test_chain_lengths software healthy tests/test_dataset.py:96
test_expected_alternatives_adjudicated_tasks software healthy tests/test_dataset.py:105
test_shared_system_prompt software healthy tests/test_dataset.py:119
test_multi_step_tasks_have_real_history software healthy tests/test_dataset.py:128
test_tool_message_contents_are_json software healthy tests/test_dataset.py:141
_calls software healthy tests/test_dataset.py:148
by_id software healthy tests/test_dataset.py:160
test_observed_haiku_dispute_fanout_credited software healthy tests/test_dataset.py:163
test_observed_haiku_tri_fanout_credited software healthy tests/test_dataset.py:189
test_truncated_counterparty_value_rejected software healthy tests/test_dataset.py:207
test_extra_filter_key_rejected software healthy tests/test_dataset.py:231
test_two_calls_on_tri_rejected software healthy tests/test_dataset.py:258
ollama_available software healthy tests/test_adapters.py:29
test_openai_adapter software healthy tests/test_adapters.py:41
test_anthropic_adapter software healthy tests/test_adapters.py:53
test_ollama_adapter software healthy tests/test_adapters.py:66
test_unknown_provider software healthy tests/test_adapters.py:78
__init__ software healthy tests/test_eval_runner.py:23
complete software healthy tests/test_eval_runner.py:27
_make_task software healthy tests/test_eval_runner.py:48
_make_response software healthy tests/test_eval_runner.py:62
test_scoring_flow software healthy tests/test_eval_runner.py:84
test_cost_attribution_uses_response_model software healthy tests/test_eval_runner.py:106
test_cpc_none_when_zero_correct software healthy tests/test_eval_runner.py:130
test_effort_passed_through software healthy tests/test_eval_runner.py:138
test_effort_omitted_by_default software healthy tests/test_eval_runner.py:143
test_results_json_written software healthy tests/test_eval_runner.py:150
_make_summary software healthy tests/test_eval_runner.py:168
test_summary_carries_metadata software healthy tests/test_eval_runner.py:184
test_artifact_timestamp_matches_filename software healthy tests/test_eval_runner.py:197
test_rep_suffix_disambiguates_filenames software healthy tests/test_eval_runner.py:203
test_median_min_max software healthy tests/test_eval_runner.py:214
test_cpc_skips_none_reps software healthy tests/test_eval_runner.py:229
test_all_none_cpc software healthy tests/test_eval_runner.py:243
test_simple_messages_pass_through software healthy tests/test_message_conversion.py:138
test_null_content_becomes_empty_string software healthy tests/test_message_conversion.py:142
test_tool_calls_get_ids_and_json_arguments software healthy tests/test_message_conversion.py:68
test_tool_results_link_to_calls_in_order software healthy tests/test_message_conversion.py:77
test_parallel_batch_results_pair_fifo software healthy tests/test_message_conversion.py:83
test_system_extracted software healthy tests/test_message_conversion.py:92
test_tool_calls_become_tool_use_blocks software healthy tests/test_message_conversion.py:97
test_tool_role_becomes_user_tool_result software healthy tests/test_message_conversion.py:107
test_second_result_links_to_second_call software healthy tests/test_message_conversion.py:116
test_no_tool_role_remains software healthy tests/test_message_conversion.py:120
test_parallel_batch_results_merge_into_one_user_message software healthy tests/test_message_conversion.py:124

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

LabelLayerStatusPath
TestParallelAlternativesAgainstDataset software healthy tests/test_dataset.py:154
StubAdapter software healthy tests/test_eval_runner.py:18
TestRunEval software healthy tests/test_eval_runner.py:83
TestWriteResults software healthy tests/test_eval_runner.py:149
TestRunMetadata software healthy tests/test_eval_runner.py:183
TestAggregateSummaries software healthy tests/test_eval_runner.py:213
TestOpenAIConversion software healthy tests/test_message_conversion.py:58
TestAnthropicConversion software healthy tests/test_message_conversion.py:91
TestOllamaConversion software healthy tests/test_message_conversion.py:137
TestWilsonInterval software healthy tests/test_aggregate_reps.py:45
TestScoreStats software healthy tests/test_aggregate_reps.py:79
TestGrouping software healthy tests/test_aggregate_reps.py:119
TestAggregateFromFiles software healthy tests/test_aggregate_reps.py:152
TestScoreTask software healthy tests/test_scorer.py:25
TestExpectedAlternatives software healthy tests/test_scorer.py:484
TestExpectedParallel software healthy tests/test_scorer.py:615
TestMatchKeywordsNestedOr software healthy tests/test_scorer.py:814
TestExpectedParallelNestedOr software healthy tests/test_scorer.py:842
TestParallelPerSpecAlternatives software healthy tests/test_scorer.py:907
TestPricingEntries software healthy tests/test_pricing.py:11
TestCostUsd software healthy tests/test_pricing.py:47
TestGetPricing software healthy tests/test_pricing.py:58
_FakeUsage software healthy tests/test_anthropic_adapter.py:22
_FakeBlock software healthy tests/test_anthropic_adapter.py:28
_FakeResponse software healthy tests/test_anthropic_adapter.py:33
_FakeMessages software healthy tests/test_anthropic_adapter.py:43
_FakeClient software healthy tests/test_anthropic_adapter.py:52
TestParamGuards software healthy tests/test_anthropic_adapter.py:64
WilsonInterval software healthy viz/aggregate_reps.py:52
ConfigStats software healthy viz/aggregate_reps.py:64
ModelPricing software healthy src/pricing.py:8
TaskRunRecord software healthy src/eval_runner.py:35
RunSummary software healthy src/eval_runner.py:45
RunAggregate software healthy src/eval_runner.py:61
ArgMatchType software healthy src/tasks.py:23
ExpectedArg software healthy src/tasks.py:28
ExpectedCall software healthy src/tasks.py:34
Task software healthy src/tasks.py:43
TaskResult software healthy src/scorer.py:36
OpenAIAdapter software healthy src/adapters/openai.py:64
AnthropicAdapter software healthy src/adapters/anthropic.py:76
Provider software healthy src/adapters/base.py:10
ToolCall software healthy src/adapters/base.py:16
LLMResponse software healthy src/adapters/base.py:21
LLMAdapter software healthy src/adapters/base.py:34
OllamaAdapter software healthy src/adapters/ollama.py:37

LabelLayerStatusPath
requirements-dev.txt software healthy requirements-dev.txt
README.md software healthy README.md
CLAUDE.md software healthy CLAUDE.md
.env.example software healthy .env.example
pyproject.toml software healthy pyproject.toml
Makefile software healthy Makefile
requirements.txt software healthy requirements.txt
test_dataset.py software healthy tests/test_dataset.py
test_adapters.py software healthy tests/test_adapters.py
__init__.py software healthy tests/__init__.py
test_eval_runner.py software healthy tests/test_eval_runner.py
test_message_conversion.py software healthy tests/test_message_conversion.py
test_aggregate_reps.py software healthy tests/test_aggregate_reps.py
test_task_loading.py software healthy tests/test_task_loading.py
test_scorer.py software healthy tests/test_scorer.py
test_pricing.py software healthy tests/test_pricing.py
test_tools.py software healthy tests/test_tools.py
test_anthropic_adapter.py software healthy tests/test_anthropic_adapter.py
2026-06-13-cpc-dashboard-redesign-design.md software healthy docs/superpowers/specs/2026-06-13-cpc-dashboard-redesign-de…
hardening-roadmap-2026-06-12.md software healthy viz/hardening-roadmap-2026-06-12.md
deploy_pages.sh software healthy viz/deploy_pages.sh
export_bench_data.py software healthy viz/export_bench_data.py
build_visualizer.py software healthy viz/build_visualizer.py
README.md software healthy viz/README.md
dashboard.html software healthy viz/dashboard.html
aggregate_reps.py software healthy viz/aggregate_reps.py
insights-2026-06-12.md software healthy viz/insights-2026-06-12.md
insights-framework-cpc.md software healthy viz/insights-framework-cpc.md
insights-2026-06-12-r2.md software healthy viz/insights-2026-06-12-r2.md
deploy-dashboard.yml software healthy .github/workflows/deploy-dashboard.yml
ci.yml software healthy .github/workflows/ci.yml
__init__.py software healthy src/__init__.py
pricing.py software healthy src/pricing.py
eval_runner.py software healthy src/eval_runner.py
tools.py software healthy src/tools.py
tasks.py software healthy src/tasks.py
cli.py software healthy src/cli.py
scorer.py software healthy src/scorer.py
openai.py software healthy src/adapters/openai.py
anthropic.py software healthy src/adapters/anthropic.py
__init__.py software healthy src/adapters/__init__.py
base.py software healthy src/adapters/base.py
ollama.py software healthy src/adapters/ollama.py
CLAUDE.md quality healthy CLAUDE.md

LabelLayerStatusPath
tests software healthy tests
docs software healthy docs
superpowers software healthy docs/superpowers
specs software healthy docs/superpowers/specs
viz software healthy viz
.github software healthy .github
workflows software healthy .github/workflows
src software healthy src
adapters software healthy src/adapters

LabelLayerStatusPath
gha::deploy-dashboard cicd healthy .github/workflows/deploy-dashboard.yml
gha::ci cicd healthy .github/workflows/ci.yml

LabelLayerStatusPath
deploy cicd healthy .github/workflows/deploy-dashboard.yml
lint cicd healthy .github/workflows/ci.yml

LabelLayerStatusPath
repobility-clone-z2_32zyq software healthy /tmp/repobility-clone-z2_32zyq

LabelLayerStatusPath
vps::azure hardware healthy CLAUDE.md

LabelLayerStatusPath
CLOUDFLARE_API_TOKEN cicd healthy —
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/bd5d3e9a-7d48-491b-8f0b-193409401b8c/

To check status programmatically (no auth required): 

curl -s https://repobility.com/api/v1/public/scan/bd5d3e9a-7d48-491b-8f0b-193409401b8c/

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.