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 commands/higoralves/orc/debuggit clone --depth 1 https://github.com/HigorAlves/orcWhat 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 | $0.00053 | $0.02168 |
| Opus 5 | $0.00026 | $0.01084 |
| Sonnet 5 | $0.00011 | $0.00434 |
| Haiku 4.5 | $0.00005 | $0.00217 |
Grade A, and why
debug 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 — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/orc:debug
Hard bugs and unexpected failures get the systematic-debugging discipline. NO FIXES WITHOUT A ROOT CAUSE.
Arguments
--jira <KEY>— link a Jira ticket key (e.g.BUG-42) to this session silently. Suppresses the Phase 1 link prompt.- The bug description / failing test name is the rest of the argument string.
Workflow
Phase 0 — Detect context
!orc-workspace-detect --banner
Context is injected above (ORC_* vars are exported for any Bash you run — do not re-run detection).
In workspace mode, resolve targetRepos from flags or via AskUserQuestion. The default is the symptom-repo (the repo where the bug surfaces) plus any sibling repos the user suspects might be the actual cause — the investigator reads across all of them. Iron rule: no silent broadcast — confirm.
Phase 1 — Initialize workspace + link
- Determine the current branch:
git branch --show-current(in workspace mode, prompt the user since cwd has no branch). Sanitize (/→-). - Create
${ORC_STATE_DIR}/<sanitized-branch>/files/if it doesn't exist. In workspace mode, also create per-repo<workspaceRoot>/<repo>/.orc/<sanitized-branch>/withworkspace-link.jsonback-pointers for each target repo (the diagnosis is workspace-level; remediation slices land per repo). - Resolve the Jira link.
- If
--jira <KEY>was passed: validate against^[A-Z][A-Z0-9_]*-\d+$. Reject and stop on mismatch. - Otherwise: ask via
AskUserQuestion— "Link a Jira ticket to this session?" with options:Paste a key/Skip — I'll bind later via /orc:jira bind/No ticket — this work has no tracker entry.
- If
- Register state:
orc-state init --command debug --total-phases 7 [--jira <KEY>]. Defer toorc:state-protocolfor schema and rules; per phase,orc-state phase set <n>+orc-state digest write -.
Phase 2 — Investigate (no fixes)
Prime code discovery first (optional, non-blocking). Follow orc:code-discovery: if graphify is installed, ensure a fresh graph on the buggy branch before dispatching — build if missing (graphify extract . --code-only) or refresh if stale (graphify update .), so the investigator queries the graph from turn one instead of discovering staleness mid-investigation. Skip silently if graphify is absent or the build fails.
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 · 139 lines · 53 tokens per session scan A dfef57d8dfee
debug is a command published in the GitHub repository HigorAlves/orc (6 stars, last pushed 5d ago), licensed MIT. It adds 53 tokens to every session and 2,168 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 commands, from other repositories
setup
Set up Postman MCP Server. Authenticate via OAuth or API key, verify connection, select workspace.
test
Run Postman collection tests, analyze results, diagnose failures, and suggest fixes.
refine-title
深度分析 Issue 或 PR 内容，并将其标题重构为 Conventional Commits 格式.
get-flow-run
Inspect a Postman Flow run by its Run ID — per-block logs, failing block, and status.
warden-cost
Dollar accounting — what does each active rule actually save, in money? Translates the token-measured verdict into dollars using a price table and the agent's own token-type mix, with a per-session net and a break-even. Read-only; spends no tokens.
routine
Execute one maintenance routine defined in scv/routines/ .md (task + guardrails + exit-criteria contract), or list defined routines. SCV never schedules — pair with host features like /loop or cron yourself. Use whenever the user asks to run a recurring maintenance task, or asks what routines exist — not only when…