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/commands/higoralves/orc/context)<a href="https://agentmods.dev/commands/higoralves/orc/context"><img src="https://agentmods.dev/badge/commands/higoralves/orc/context/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/commands/higoralves/orc/context"><img src="https://agentmods.dev/badge/commands/higoralves/orc/context.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 | $0.00020 | $0.00839 |
| Opus 5.5 | $0.00008 | $0.00336 |
| Sonnet 5.5 | $0.00004 | $0.00168 |
| Haiku 4.5 | $0.00002 | $0.00084 |
Grade A, and why
context 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 — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/orc:context
Maintain docs/agents/project-context.md, the committed file that survives every branch. Contract, sections, cap and line rubric live in orc:project-context.
Arguments
generate(default): interview the repo and write the file. Refuses when the file exists.show: print the file and its size against the cap. Read-only.refresh: re-derive the file and gate on the diff.add-rule "<text>": append one rule./orc:retrocalls this path.--section <name>: withadd-rule, the target section.
Preconditions
- Invoke
orc:project-contextfirst. - Target path is
docs/agents/project-context.mdin the current repo. - A missing file is not an error for
show: say so and offergenerate.
Workflow
generate
- Prime discovery per
orc:code-discovery; fall back to Glob and Grep silently. - Derive the stack from manifests, lockfiles and CI runtimes.
- Derive the test, lint, typecheck and build commands from CI scripts, Makefile and package scripts.
- Derive conventions from the real source tree. The code wins over the README.
- Derive binding rules from CI gate scripts, hooks and
CONTRIBUTING.md. - Drop every line that fails the rubric in the FORMAT.md reference of
orc:project-context. - Write the cap in the file header: 150 lines / 6 KB.
- Print the gate below, then the full draft.
- Write the file only after approval.
- Print the size line.
⛔ Gate — project context
lines against the 150-line cap, path
docs/agents/project-context.md.
Ask with AskUserQuestion: Write it, Trim first, Cancel. This gate asks at every autopilot level. The file steers every later agent.
refresh
- Read the existing file.
- Keep every
<!-- human -->line and everything under## Notesuntouched. - Re-derive the rest as in generate steps 1 to 6.
- Say "project-context.md is current" and stop when nothing differs.
- Gate on the diff with
AskUserQuestion: accept all, pick hunks, cancel. - Write the file and print the size line.
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 First seen · 87 lines · 20 tokens per session scan A e0428834db08
context is a command published in the GitHub repository HigorAlves/orc (7 stars, last pushed yesterday), licensed MIT. It adds 20 tokens to every session and 839 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 2026-10-24.
Other commands, from other repositories
status
A project-status command that checks a code repository and its supporting project notes. The supplied description is in Chinese and lists checks for Git, a memory bank, dependencies, environment settings, components, and conflicts.
atlas
Cross-project atlas with an adaptive render — ≤4 projects in scope get detail cards, more get one aligned digest line each, grouped by domain. Facets projects · sessions · memory · plans · specs · plugins · claude.md; a bare run renders all of them except plugins (opt-in, machine-global). --dir NAME|PATH anchors the…
thread
Persistent context threads for cross-session work that spans phases. Lighter than pause/resume.
show
Show this project's saved Recall context (.recall/context.md).
handoff
Write a session handoff document for continuity.
scout-meta-review
Run an interactive Scout meta-review — a system-level audit that sits above the individual session types. Checks whether sessions are running, mistake audit is trending well, proposals are flowing, KB files are healthy, and data-source coverage is consistent across session types. Runs in the current conversation.