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/clay-good/openlore/orientgit clone --depth 1 https://github.com/clay-good/OpenLoreWhat 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 | $0.00022 | $0.01052 |
| Opus 5 | $0.00011 | $0.00526 |
| Sonnet 5 | $0.00004 | $0.00210 |
| Haiku 4.5 | $0.00002 | $0.00105 |
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.
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.
openlore: Pre-flight Check
Run this command before /speckit.implement on an existing codebase.
It identifies the functions affected by the planned tasks, scores their blast radius,
and surfaces any spec requirements that apply — so you don't discover high-risk
areas mid-implementation.
Greenfield projects (no existing codebase): skip this command. It is only useful when implementing against an existing codebase.
Prerequisites
- openlore MCP server configured in your AI agent settings
openlore analyzerun at least once on the project directory (produces the.openlore/cache used by orient)
User Input
$ARGUMENTS
If a project directory is provided, use it. Otherwise use the current working directory.
Step 1 — Read tasks.md
Read .specify/{feature}/tasks.md to extract the list of planned tasks.
Summarise the implementation intent in one sentence — this is the $TASK_DESCRIPTION
passed to orient.
If tasks.md does not exist, ask the user for a brief description of what they are about to implement.
Step 2 — Orient
openlore orient
directory: $PROJECT_ROOT
task: $TASK_DESCRIPTION
limit: 7
If orient returns "error": "no cache":
"openlore has no analysis cache for this project. Run
openlore analyze $PROJECT_ROOTfirst (takes ~1 min), then re-run/speckit.openlore.orient." Stop here.
Step 3 — Check spec baseline
Check whether OpenSpec specifications exist for this project:
ls $PROJECT_ROOT/openspec/specs/ 2>/dev/null | head -5
If no specs exist (openspec/specs/ is absent or empty):
"No OpenSpec specs found.
search_specsandcheck_spec_driftwill return empty results until specs are generated.Recommended: run
openlore generate $PROJECT_ROOTafter this sprint to create a spec baseline from the existing code. You only need to do this once — subsequent sprints will have specs to align against.Continuing with structural analysis only (orient + impact)."
If specs exist: proceed to search_specs below.
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 · 22 tokens per session scan A 438f269b95bb
orient is a command published in the GitHub repository clay-good/OpenLore (290 stars, last pushed 2d ago), licensed MIT. It adds 22 tokens to every session and 1,052 once invoked, about $0.0001 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
feature
Orchestrate a complete feature through discovery, spec, implementation, and review.
research
Research a technical or product question.
brainblast-deploy-plan
Deployment Intelligence for Anchor programs. Run before anchor deploy so you know how much SOL you need and the exact ordered transaction sequence — instead of working it out by hand.
review
Review the current diff against project memory.
screens
Structures product UX screen design — inventory, flow, states, and reusable briefs for external design tools — without generating pixels or UI code.
adr-supersede
Create a new ADR that supersedes an existing one.