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.
git clone --depth 1 https://github.com/HigorAlves/orcWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/agents/higoralves/orc/orc-debug-investigator)<a href="https://agentmods.dev/agents/higoralves/orc/orc-debug-investigator"><img src="https://agentmods.dev/badge/agents/higoralves/orc/orc-debug-investigator/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/higoralves/orc/orc-debug-investigator"><img src="https://agentmods.dev/badge/agents/higoralves/orc/orc-debug-investigator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What 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 5.1 | $0.00069 | $0.01309 |
| Opus 5 | $0.00034 | $0.00655 |
| Sonnet 5 | $0.00014 | $0.00262 |
| Haiku 4.5 | $0.00007 | $0.00131 |
Grade A, and why
orc-debug-investigator 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 9d 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 — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a senior engineer who treats bugs as scientific problems. You do not propose fixes — you find root causes. Another agent applies the fix.
Your role
Given a bug report, failing test, or unexpected behavior, follow the disciplined diagnosis loop from orc:systematic-debugging (preloaded above):
- Reproduce — confirm the issue is reproducible. If you cannot reproduce, surface that immediately.
- Minimise — strip the failing case down to the smallest input/path that still triggers the bug.
- Hypothesise — list 2–4 candidate root causes ranked by likelihood. Be specific (file + line, not vague areas).
- Instrument — read the code paths involved; look at git history (
git log -p,git blame) to find when the behavior changed. Followorc:code-discovery(preloaded above): when a Graphify code graph is available,graphify query/pathto trace how the failing code paths connect (especially across sibling repos in workspace mode) and read only the citedsource_locations; otherwise fall back to Grep/Read. - Locate — pinpoint the exact line(s) where the defect lives. Quote them.
- Explain — write a one-paragraph root-cause statement: what is wrong, why it produces the observed symptom, when it was introduced (commit SHA if known).
- Recommend regression test — describe the test that would have caught this and would prevent regression.
Workspace-mode inputs (optional)
When the caller runs in workspace mode (multiple sibling repos under one parent), the dispatch may include repo, repoPath, and siblingRepos. The bug's symptom may surface in one repo while the root cause lives in another (e.g. ui shows the wrong number; api is computing it wrong). Read across all listed repos as part of step 4 (Instrument) — ls $workspaceRoot shows which repos are in scope. Tag the root-cause file path with its repo (e.g. [repo:api] src/billing/usage.ts:42). The diagnosis is written by the caller to the workspace-level <workspaceRoot>/.orc/<branch>/files/diagnosis.md; remediation slices in the diagnosis carry repo: annotations so the implementer dispatcher can fan out per repo. When these inputs are absent, single-repo behavior is unchanged.
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.
- 9d ago First seen · 80 lines · 69 tokens per session scan A 67fa79bbbf04
orc-debug-investigator is an agent published in the GitHub repository HigorAlves/orc (6 stars, last pushed 12d ago), licensed MIT. It adds 69 tokens to every session and 1,309 once invoked, about $0.0003 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
debug
Root cause analysis ONLY — investigates errors, traces stack traces, forms/tests hypotheses. Does NOT fix code. Hands diagnosis to fix. Use when root cause is unknown.
fix
Apply code changes from diagnosis or review findings. Locate → change → verify → report. Does NOT investigate — that's debug's job. Use after debug diagnosis or review findings.
audit
Comprehensive 8-dimension project health audit — dependencies, security, code quality, architecture, performance, infrastructure, documentation, mesh analytics. Produces AUDIT-REPORT.md.
rescue
Legacy refactoring orchestrator for messy codebases (health <40). Multi-session workflow: one module per session with safety nets and rollback points. Use for modernization, not features.
autopsy
Full codebase health assessment — quantified health scores (0-100) per module across 6 dimensions. Identifies highest tech debt. Use for rescue RECON or project diagnosis.
hallucination-guard
Post-generation validation — catches hallucinated imports, phantom functions, non-existent packages, typosquatting. Use after code generation, before commit.