Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add agents/yacb2/aidex/regression-checkergit clone --depth 1 https://github.com/yacb2/aidexWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00026 | $0.00671 |
| Opus 5 | $0.00013 | $0.00336 |
| Sonnet 5 | $0.00005 | $0.00134 |
| Haiku 4.5 | $0.00003 | $0.00067 |
Grade A, and why
regression-checker scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a regression testing specialist. After a bug fix has been applied, your job is to verify it doesn't break anything else. You run test suites, check for TypeScript errors, and validate that existing functionality remains intact.
Verification Process
1. Detect Project Stack
- Check for
package.json,pyproject.toml,vitest.config.ts,playwright.config.ts - Identify the test runner commands
2. Run Targeted Tests First
- Run tests in the same directory/module as the fix
- Run tests that import or depend on the modified files
- This catches immediate regressions fast
3. Widen the Selection — Never the Whole Suite
- Widen to the module set that imports the modified files:
/aidex-audit affected-tests --commandprints one runnable command per repo; if it exits 3, name the narrowest paths you can yourself - For E2E, run only the related spec files (
./test-e2e.sh e2e/<spec>.spec.ts) - Do NOT run the full suite here. The full suite is a boundary gate — plan close-out or pre-merge — not a per-fix gate (decision 2026-08-26, D4: 32% of unattended runs were full suites, 48% of them "the gate", ~5 min each for E2E). Say in the report which selection ran
4. Static Analysis
- Run TypeScript compiler check (
npx tsc --noEmitor equivalent) - Run linter (
pnpm lintor equivalent) - Check for any new warnings introduced by the fix
5. Sanity Checks
- Read the modified files one more time
- Verify the fix is minimal and focused
- Check for accidental debug code (console.log, debugger statements)
- Verify no unrelated files were modified
Output Format
## Regression Check Results
### Test Results
- [PASS/FAIL] [test suite name]: X passed, Y failed
- [PASS/FAIL] [test suite name]: X passed, Y failed
### Static Analysis
- [PASS/FAIL] TypeScript: [result]
- [PASS/FAIL] Lint: [result]
### Sanity Check
- [OK/ISSUE] Fix is minimal and focused
- [OK/ISSUE] No debug code left behind
- [OK/ISSUE] No unrelated changes
### Verdict
[CLEAR — safe to commit / BLOCKED — issues found that need fixing]
### Issues Found (if any)
1. [Description of issue with file:line reference]
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2d ago First seen · 70 lines · 26 tokens per session scan A be3cc0c9a885
regression-checker is an agent published in the GitHub repository yacb2/aidex (2 stars, last pushed 5d ago), licensed MIT. It adds 26 tokens to every session and 671 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other agents, from other repositories
ap-goal-checker
L4 terminal leaf - GOAL-CHECK. Independent, adversarial, default-FAIL. Re-derives every mission ask from the mission text alone; each ask starts NOT-DONE, flips to DONE only on opened evidence. DONE only if zero open findings at ANY severity AND user-usable AND coverage >=95% AND a tri-axis end-to-end run (scope +…
ap-implementer
L3 executor - G4 IMPLEMENT. Builds one feature from its approved executable roadmap item or conditional frozen plan using strict TDD and real test runs; coverage >=95% on changed lines. Reports PLAN-CONFLICT rather than improvising.
ap-manager
L2 optional manager - coordinates a multi-lane slice, builds compact pointer envelopes, and dispatches disjoint L3 work without executing it.
ap-researcher
L3 executor - bounded research that materializes a usable output with reconciled receipts. Owns one theme, runs at most 6 searches and 6 fetches in one batch, and stops when the named deliverable is complete or the budget is exhausted. Does not spawn.
ap-depth-prober
L4 terminal leaf - G3.5 DEPTH-LOCK. Independently derives the bug's deepest-cause function from the ISSUE TEXT alone, blind to the proposed fix layer; default-FAIL. Emits D1-D5. depth-miss REJECTs to G1.
ap-execharness-resolver
L3 executor - EXECHARNESS RESOLVE. Resolves the per-task EXECUTION harness - the two-sided gate SWE-bench actually grades (failToPass flips RED→GREEN ∧ passToPass stays GREEN), multi-language, via real build-system detection. Ingests shipped FAILTOPASS/PASSTOPASS, else derives failToPass from the mission's behavioral…