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/andyzengmath/soliton/co-changegit clone --depth 1 https://github.com/andyzengmath/solitonWrote 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/andyzengmath/soliton/co-change)<a href="https://agentmods.dev/commands/andyzengmath/soliton/co-change"><img src="https://agentmods.dev/badge/commands/andyzengmath/soliton/co-change.svg" alt="Measured on agentmods" 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 | $0.00018 | $0.00667 |
| Opus 5 | $0.00009 | $0.00333 |
| Sonnet 5 | $0.00004 | $0.00133 |
| Haiku 4.5 | $0.00002 | $0.00067 |
Grade A, and why
co-change 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 4d 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 — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/co-change
List the files that have historically been changed in the same commits as a target file. Uses git log as a degraded-mode CO_CHANGE proxy — a standalone heuristic inspired by CO_CHANGE graph semantics (note: the historical-context agent uses git history for bug-fix frequency / churn / blame patterns, NOT for co-occurrence; this command introduces the per-file co-change query separately). Will upgrade to true CO_CHANGE graph edges when available per POST_V2_FOLLOWUPS §B1.
Argument
<file>— path to a file in the current repository.
Behavior
-
Validate input: if
<file>is missing or doesn't exist, outputError: file not found: <file>and STOP. -
Find co-change candidates via git log:
git log --name-only --pretty=format: --since="6 months ago" -- "<file>"This returns every file ever changed in a commit that also touched
<file>. -
Count co-occurrence frequency:
- Strip blank lines and the input file itself
- Aggregate counts: how many times each candidate file was in a same-commit grouping with
<file> - Sort by frequency descending
-
Output the top-10 co-changers:
Co-change for <file> (last 6 months, git log heuristic)
| Rank | Co-changer | Count |
|------|------------|-------|
| 1 | path/x.ts | 12 |
| 2 | path/y.ts | 9 |
| ... | ... | ... |
Backing source: git log (graph plugin pending §B1; will upgrade to CO_CHANGE edges from graph-code-indexing when available).
If 0 candidates: "No co-changers found — file may be new (< 6 months of history), rarely modified, or always changed in isolation."
Use cases
- Pre-PR sanity check: before opening a PR that modifies
auth/session.py, see which files historically move together — likely candidates for downstream regression checks. - Onboarding: when joining a project,
/co-change <core-file>reveals which files form natural cohort sets. - Refactor scope: planning a rename of
<file>? Co-change list approximates the touch surface.
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.
- 4d ago First seen · 58 lines · 18 tokens per session scan A f55271ebf5ba
co-change is a command published in the GitHub repository andyzengmath/soliton (1 stars, last pushed 2mo ago), licensed MIT. It adds 18 tokens to every session and 667 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
archetype-impact
Scan the current workspace for all references to a given archetype across templates (.oet / .t.json source, .opt compiled) and AQL files, producing an impact table useful before editing a widely-reused archetype.
openehr-explain
One-stop router that explains or looks up any openEHR thing — auto-detects an archetype, a template, an RM/AM/BASE type, an RM structural concept, an ADL idiom, an AQL query or keyword, or a terminology code (replaces /archetype-explain, /template-explain, /type-spec, /rm-structure, /adl-idiom, /terminology).
ckm-search
Search the openEHR Clinical Knowledge Manager (CKM) for archetypes or templates.
ship-an-mcp-server
Workflow recipe — make your product agent-usable by chaining 4 skills, spec to pricing.
rescue-an-account
Workflow recipe — diagnose an at-risk customer and build the full save play through to renewal by chaining 4 skills.
nyann:diff-profile
Compare two nyann profiles side-by-side and show what changes between them: hooks, branching, CI, documentation, extras, governance. Useful before switching profiles to understand the impact.