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/tacoda/keystone/orientgit clone --depth 1 https://github.com/tacoda/keystoneWhat 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 | $0.00005 | $0.00502 |
| Opus 5 | $0.00003 | $0.00251 |
| Sonnet 5 | $0.00001 | $0.00100 |
| Haiku 4.5 | $0.00001 | $0.00050 |
Grade A, and why
orient 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
orient
Enter the planning phase. Load codebase state and matching idioms for the touched region, then sketch a plan. Read .charter/guides/process/planning.md for the full discipline.
Activities
- Read
.charter/corpus/state/CODEBASE_STATE.mdto learn:- Tool commands (lint, type-check, test, build)
- Stacks present in the codebase
- Regions and their applicable idioms
- Identify the touched region(s) and touched-files set for this task. Map regions to stacks in
CODEBASE_STATE.md; the touched-files set is the list of paths the task will read or edit. - Read
.charter/corpus/state/GLOBS_INDEX.md— the reverse-index of guideglobs:. For each pattern in the index, check whether any touched file matches; collect the union of matched guides as the globs-loaded set. - Load matching idioms. For each stack the task touches, walk
.charter/guides/idioms/<stack>/*.md. Load each guide unless it declaredglobs:and it isn't in the globs-loaded set from step 3. (Guides withoutglobs:keep today's stack-based loading; guides withglobs:load only when their patterns matched.) Read the corresponding.charter/corpus/idioms/<stack>/<name>.mdfor each loaded guide when you need the reasoning. - Load active migrations for the touched region (
.charter/corpus/state/migrations/active/*.md). - Sketch a plan — step list with a verification check per step.
Gate
Do not begin implementation until the user has accepted the plan.
What to not load
- Idioms for stacks the task does not touch.
- Idioms whose
globs:did not match any touched file (per step 3). - Process docs for phases this task is not currently in.
Orient exists to keep context small and relevant. Reading the entire corpus on every task is what orient prevents. The globs-index lookup tightens that further — a guide that declares globs: enters context only when its claimed paths are actually being touched.
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 · 33 lines · 5 tokens per session scan A b2726f7ed45c
orient is a command published in the GitHub repository tacoda/keystone (44 stars, last pushed 2mo ago), licensed MIT. It adds 5 tokens to every session and 502 once invoked, about $0.0000 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 2026-08-30.
Other commands, from other repositories
git
Git operations with intelligent commit messages and workflow optimization.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.