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 skills add HigorAlves/orc --skill mapgit 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/skills/higoralves/orc/map)<a href="https://agentmods.dev/skills/higoralves/orc/map"><img src="https://agentmods.dev/badge/skills/higoralves/orc/map/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/skills/higoralves/orc/map"><img src="https://agentmods.dev/badge/skills/higoralves/orc/map.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 | $0.00024 | $0.01173 |
| Opus 5.5 | $0.00010 | $0.00469 |
| Sonnet 5.5 | $0.00005 | $0.00235 |
| Haiku 4.5 | $0.00002 | $0.00117 |
Grade A, and why
map 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 yesterday.
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 — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
The orc map
Which orc thing do I reach for? Answer from this map — recommend ONE entry point (➡️), name the runner-up only when the choice is genuinely close.
Before stating what a command or skill does, or recommending one of its steps be skipped, read its file: the summaries here are for orientation only.
The main flow (idea → shipped)
Step-by-step, human at every gate:
/orc:prd → /orc:trd → /orc:plan → /orc:start → implement → /orc:qa → /orc:ship → /orc:ci → /orc:address → /orc:cleanup
Most work enters mid-flow — a settled spec starts at /orc:plan; a settled
plan starts at /orc:start. The one-shot alternative: /orc:flow runs the
whole pipeline (plan → implement → QA → ship → address → cleanup) with an
interactive gate per phase. Prefer /orc:flow when you want to hand over a
well-described feature; prefer the step commands when you want to steer.
/orc:explain is the optional step after QA: a narrated walkthrough of what
was built and proven.
On-ramps (how work arrives)
| Situation | Entry point |
|---|---|
| Report in (ticket, Sentry, paste): is it real? | /orc:triage |
| Confirmed bug, failing test, weird behavior | /orc:debug (root cause before fix) |
| Production is on fire RIGHT NOW | /orc:incident → later /orc:postmortem |
| CI red on an open PR | /orc:ci |
| Someone's PR needs review | /orc:code-review |
| Reviewers commented on YOUR PR | /orc:address |
| PRD/spec/brief landed | /orc:plan (dispatches analysis as needed) |
| "Where's the rot?" / refactor appetite | /orc:plan, refactor framing (orc-refactor-architect) |
| Chunk of work too big for one session | /orc:wayfinder |
| Issue backlog needs herding | /orc:triage |
| Feature needs a Jira Epic→Story→Task build-out | /orc:jira-breakdown |
| Dependencies stale or vulnerable | /orc:deps |
| Need a narrated video of what shipped | /orc:explain (after /orc:qa) |
| Cut a release (user project) | /orc:release |
| New package/service/app shell | /orc:scaffold |
| Interrupted mid-anything | /orc:resume (/orc:status lists what's live) |
| A build just finished (or went sideways) | /orc:retro — improve the environment, not the code |
| Agents keep relearning the same conventions | /orc:context — write the binding project-context.md |
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.
- yesterday Changed · +1 lines 269e987fa62f
- 4d ago Changed · +4 lines 33d0dfc9f167
- 17d ago Changed · +3 lines 3f8657798138
- 19d ago Changed 4d53c6dd1386
- 1mo ago First seen · 83 lines · 24 tokens per session scan A 580c741cbea0
map is a skill published in the GitHub repository HigorAlves/orc (7 stars, last pushed yesterday), licensed MIT. It adds 24 tokens to every session and 1,173 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-09-03.
Other skills, from other repositories
session-save
Save the current session state (decisions, modified files, current status, and next steps) to a handoff file for later resume.
handoff-update
Update an existing handoff document with current session progress. Applies section-specific merge rules: append-only for Work Done (never deletes history), replace for Status and Next Steps, merge for Files and Discoveries. Falls back to creating a new handoff if no source file is found.
monday-planning
Suggest a weekly training structure from recent load and deliver the plan.
figure-out
Figure things out together — any topic, problem, or idea. Presses relentlessly until shared understanding is reached. Use when understanding is the deliverable rather than a preamble to acting, when figuring it out is the goal, or when the user asks to think through a decision, dig deeper, press an assumption…
token-check
Estimate how many tokens a pasted text, an attached file or the conversation so far takes, what it means for the context window and usage limits, and how to cut it. Use when the user asks how big something is in tokens, why they keep hitting limits, or whether a file is too large to send.
escalate
Terminal escalation for do when unresolved blockers require outside intervention and no useful independent work remains. Reports the evidence, recovery attempts, completed work, and intervention needed.