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/melagiri/code-insights/releasegit clone --depth 1 https://github.com/melagiri/code-insightsWhat 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 | $0.01713 |
| Opus 5 | $0.00000 | $0.00856 |
| Sonnet 5 | $0.00000 | $0.00343 |
| Haiku 4.5 | $0.00000 | $0.00171 |
Grade A, and why
release 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 — 244 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/release — Automated Release Workflow
Arguments: $ARGUMENTS
You are executing the release workflow for @code-insights/cli. Parse $ARGUMENTS to extract:
- type (required):
patch,minor, ormajor - description (optional): A one-liner for the release title
If type is missing or not one of patch/minor/major, ask the user to provide it.
Step 1: Pre-flight Checks
Run ALL of these checks. If any fail, STOP and tell the user what to fix.
# Must be on master
git branch --show-current # Must output "master"
# Must have clean working tree
git status --porcelain # Must be empty
# Pull latest
git pull origin master
Read the current version from cli/package.json (the "version" field).
Compute the new version:
patch: increment the third number (3.6.1 → 3.6.2)minor: increment the second number, reset third to 0 (3.6.1 → 3.7.0)major: increment the first number, reset second and third to 0 (3.6.1 → 4.0.0)
Resume detection: Run npm view @code-insights/cli version to get the currently published version. If the version in package.json is ALREADY GREATER than the npm version, this is a resumed release — skip to Step 6.
Step 2: Analyze Changes
Find the last git tag and analyze what changed:
# Find latest tag
git describe --tags --abbrev=0
# Commits since last tag
git log $(git describe --tags --abbrev=0)..HEAD --oneline
# Full diff since last tag
git diff $(git describe --tags --abbrev=0)..HEAD --stat
Read the full diff and commit messages. Then:
-
Generate a CHANGELOG entry in the existing format (see
cli/CHANGELOG.mdfor style). Group changes under### Added,### Changed,### Fixed,### Improvedas appropriate. Match the existing tone — concise but descriptive, with bold lead-ins. -
Generate a release title — a short phrase summarizing the release (e.g., "LLM-Powered Export Page", "PostHog custom domain"). Use the user's description if provided, otherwise derive from the changes.
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 · 244 lines · 0 tokens per session scan A 2aad6d941324
release is a command published in the GitHub repository melagiri/code-insights (76 stars, last pushed 3mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,713 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
lians-integrate
Wire Lians memory into the current repository with a test-driven, minimal-diff integration.
lians-audit
Run a Lians compliance/audit operation - snapshot, chain verify, backtest, or erasure.
lians-recall
Recall current (non-stale) facts from Lians memory, optionally as-of a past date.
lians-remember
Store a fact in Lians memory with its business event-time and metadata.
wrap
Close the session cleanly. Update entity state. Capture decisions. Detect momentum shifts.
focus
"What should I work on today, and why?".