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 project-contextgit 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/project-context)<a href="https://agentmods.dev/skills/higoralves/orc/project-context"><img src="https://agentmods.dev/badge/skills/higoralves/orc/project-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/skills/higoralves/orc/project-context"><img src="https://agentmods.dev/badge/skills/higoralves/orc/project-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 | $0.00035 | $0.00483 |
| Opus 5.5 | $0.00014 | $0.00193 |
| Sonnet 5.5 | $0.00007 | $0.00097 |
| Haiku 4.5 | $0.00003 | $0.00048 |
Grade A, and why
project-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 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.
What it actually says
Project Context
.orc/ dies at cleanup. docs/agents/project-context.md does not. It carries a repo's implementation conventions across branches, sessions and agents.
What it is
- Directives to agents: "use X, never Y, here".
- Project-specific facts a model would guess wrong.
- Committed, shared with the team.
It is not documentation for humans, a plan, or session state. Architecture prose belongs in docs/adr/. Vocabulary belongs in GLOSSARY.md.
Line test: would a competent engineer new to this repo get it wrong without the line? If no, cut it. Rubric and worked example: FORMAT.md.
Cap
150 lines / 6 KB, hard. Executors preload this file on every task, so the cap is a per-task token cost. State the cap in the file header. scripts/ci/verify-project-context.sh fails above 150 lines or 6144 bytes. Cut before you add.
Sections
Keep this order. Omit a section that would be empty.
- Stack & versions
- Commands (test, lint, typecheck, build)
- Critical rules
- Patterns to follow
- Patterns to avoid
- Known landmines
Binding semantics
Critical rules are binding. A slice that needs to break one escalates. The caller decides: the rule is stale, or the slice is wrong.
Other sections are strong defaults. Deviate only with a stated reason in the slice report.
Who reads it
- Four agents preload this skill:
orc-implementer,orc-test-author,orc-code-fixer,orc-qa-validator. - Each reads the file once, before discovery.
- A missing file is the default state. Proceed silently, never gate on it.
Who writes it
/orc:contextgenerates, refreshes and appends. Executors never write the file./orc:retroproposes additions from repeated incidents.- Each proposal passes the line test and the cap, and lands only through a gate.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 Changed · -2 lines 64c8260f616d
- 8d ago First seen · 54 lines · 35 tokens per session scan A e6a817a873ae
project-context is a skill published in the GitHub repository HigorAlves/orc (7 stars, last pushed yesterday), licensed MIT. It adds 35 tokens to every session and 483 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 skills, from other repositories
mappamind
Use Mappamind to set up the first workspace baseline, snapshot before an AI coding agent session, render the shift card after changes, and include local Studio/card URLs in the final response.
catchup
Restore context after /clear by summarizing recent work and project state.
knowledge-wiki
A tool that turns useful lessons from coding sessions into general articles for a team wiki. A wiki is a collection of linked reference pages, and this one can be kept locally or shared through a Git repository.
doc-digest
Turn a long document, PDF, transcript, spreadsheet or log into a compact working digest the conversation can continue from. Use when the user shares or pastes something long (several pages or more) and wants to discuss, analyze, compare or use it over more than one message, or asks to summarize a document so they can…
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.
scout-ask
Use when the working directory is a Scout vault (it has knowledge-base/ and action-items/) and the user asks about the state of a project, initiative, person, decision, meeting or open thread ("where are we on X", "what's going on with Y", "who is Z", "what's on my plate"), or what Scout knows about a topic. Do not…