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/agentis-tools/ctx/snapshotgit clone --depth 1 https://github.com/agentis-tools/ctxWhat 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 | $0.00000 | $0.02765 |
| Opus 5 | $0.00000 | $0.01383 |
| Sonnet 5 | $0.00000 | $0.00553 |
| Haiku 4.5 | $0.00000 | $0.00277 |
Grade A, and why
snapshot 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 — 220 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ctx snapshot
Capture per-commit Parquet metric snapshots for longitudinal quality analysis.
Synopsis
ctx snapshot [--force] [--churn-window <SPEC>] [--json]
ctx snapshot backfill --since <REF> [--every <N>] [--churn-window <SPEC>] [--json]
Description
Point-in-time commands like ctx score answer "did this change make the code better or worse?". ctx snapshot answers the longitudinal version: is the codebase trending better or worse over weeks and months? Each run exports the current commit's per-file and per-symbol metrics, near-duplicate pairs, and capture metadata as one Parquet partition:
.ctx/snapshots/sha=<sha>/symbols.parquet per-symbol metrics
.ctx/snapshots/sha=<sha>/files.parquet per-file metrics + churn + violations
.ctx/snapshots/sha=<sha>/dup_pairs.parquet near-duplicate function pairs
.ctx/snapshots/sha=<sha>/meta.parquet capture metadata (1 row)
Accumulate partitions over time (one per commit), then query them with ctx sql --snapshots to plot duplication, violation, and hotspot trends across the history.
A bare ctx snapshot captures HEAD: the index is refreshed incrementally first (same as ctx score), then the four Parquet files are written to a staging directory and moved into place with an atomic rename — readers never observe a half-written partition. If a partition for HEAD's sha already exists the command is a no-op (exit 0); --force rewrites it. When the working tree is dirty, a stderr warning notes that the snapshot is labeled with HEAD's sha but reflects the working tree.
Snapshot capture requires the duckdb feature (on by default); builds without it exit 2.
Options
| Option | Description | Default |
|---|---|---|
--force |
Overwrite an existing partition for HEAD | false |
--churn-window <SPEC> |
How far back to count per-file churn (a git log --since date spec) |
"90 days ago" |
--json |
Machine-readable output (global flag) | false |
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 · 220 lines · 0 tokens per session scan A 2537b695e885
snapshot is a command published in the GitHub repository agentis-tools/ctx (11 stars, last pushed 15d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 2,765 tokens. 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
coograph-review
Review the changes in scope for spec compliance, convention violations, logic bugs, and architectural issues. You review — you do not author. Never edit files.
coograph-verify
Verify that the described work is complete and correct. Provide evidence for every claim. You verify — you do not implement or fix style.
api-gen
Generate REST API endpoints with routes, validation, error handling, and tests.
component-gen
Generate React or Vue components with prop types, styling, accessibility, and tests.
code-review
Review staged git changes for bugs, security issues, and style violations.
pr-description
Generate a PR title and description from the current branch diff against main.