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/ihorkatkov/pantheon/updategit clone --depth 1 https://github.com/ihorkatkov/pantheonWhat 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 | $0.00013 | $0.00615 |
| Opus 5 | $0.00006 | $0.00308 |
| Sonnet 5 | $0.00003 | $0.00123 |
| Haiku 4.5 | $0.00001 | $0.00061 |
Grade A, and why
update 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 — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/update
You are merging upstream Pantheon updates into this workspace while preserving user customizations.
Context
The user ran make update which:
- Added
pantheon-upstreamremote pointing togithub.com/ihorkatkov/pantheon - Fetched the latest
pantheon-upstream/main - Detected a version mismatch between local and upstream
.pantheon-version - Launched you to perform the intelligent merge
What You Do
Step 1: Understand What Changed
Compare local vs upstream:
git diff HEAD...pantheon-upstream/main --stat
git diff HEAD...pantheon-upstream/main
Categorize changes:
- Agent updates:
.opencode/agents/*.md - Command updates:
.opencode/commands/*.md - Skill updates:
.opencode/skills/** - CLI updates:
pt,setup-worktree,Makefile - Config updates:
.opencode/opencode.jsonc - Doc updates:
README.md,docs/
Step 2: Identify User Customizations
Check which files the user has modified:
# Files user has changed since initial clone/last update
git log --all --diff-filter=M --name-only --pretty=format: -- .opencode/ pt setup-worktree Makefile | sort -u
Read current versions of modified files to understand user customizations.
Step 3: Merge Strategy
For each changed file:
Unmodified by user → Apply upstream change directly (overwrite with upstream version)
Modified by user → Smart merge:
- If upstream changed mythology/role sections and user changed project-specific sections → merge both
- If both changed the same section → present both versions to the user and ask which to keep
- If user added new content that upstream doesn't touch → preserve user additions
New upstream files → Add directly
Deleted upstream files → Remove (notify user if they had modifications)
Step 4: Apply Changes
- Apply non-conflicting changes
- Present conflicts for user resolution
- Update
.pantheon-versionto the upstream version
Step 5: Verify
- Ensure all agent files are valid markdown with frontmatter
- Ensure no merge artifacts (
<<<<<<<,=======,>>>>>>>) - Report: what was updated, what was preserved, what needs user attention
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 · 79 lines · 13 tokens per session scan A 85979130ad97
update is a command published in the GitHub repository ihorkatkov/pantheon (5 stars, last pushed 5mo ago), licensed MIT. It adds 13 tokens to every session and 615 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 2026-08-31.
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.