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/apetta/agent-xlsx/releasegit clone --depth 1 https://github.com/apetta/agent-xlsxWhat 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 | $0.00017 | $0.00933 |
| Opus 5 | $0.00009 | $0.00466 |
| Sonnet 5 | $0.00003 | $0.00187 |
| Haiku 4.5 | $0.00002 | $0.00093 |
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 — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
State
- Recent commits (tagged): !
git log --oneline --decorate -20 - Latest tag: !
git tag --sort=-v:refname | head -1 - Status: !
git status --short - Version: !
grep '^version' pyproject.toml
Steps
Stop and report if any step fails.
-
Pre-flight: Verify clean working tree and on
main. If there are no commits since the last tag, report "Nothing to release" and stop. -
Assess bump: Analyse all commits since the last tag:
BREAKING CHANGEor!:in any commit →major- Any
feat:commit →minor - Only
fix:,chore:,docs:,refactor:→patch - Take the highest applicable level.
- If
$ARGUMENTSis provided and matches the assessed level, proceed. - If
$ARGUMENTSis provided but disagrees with the assessment, flag the mismatch with reasoning and ask the user to confirm or revise. - If
$ARGUMENTSis empty, propose the assessed bump and ask the user to confirm.
-
Compute version: Parse current from
pyproject.toml, apply bump. Stateold → new. -
Update versions in exactly these 2 files:
pyproject.toml→version = "X.Y.Z"src/agent_xlsx/__init__.py→__version__ = "X.Y.Z"
Grep the old version string across
pyproject.tomlandsrc/to confirm zero remaining hits. -
Sync lockfile:
uv sync --group dev -
Changelog: Add entry to
docs/src/app/changelog/page.mdxbelow# Changelog, above the previous release entry. Review all commits since the previous tag. Follow the existing format and tone. Keep it concise; consolidate related fixes into single bullets. -
Validate:
uv run ruff check && uv run ruff format --check && uv run ty check && uv run pytest -v -
Commit: Stage
pyproject.toml,src/agent_xlsx/__init__.py,uv.lock, anddocs/src/app/changelog/page.mdx. Commit message:chore: release vX.Y.Z -
Tag + push:
git tag vX.Y.Z && git push origin main --tags -
GitHub release: Derive notes from the changelog entry. Use
gh release create vX.Y.Z --title "vX.Y.Z" --notes "..."(note: the flag is--notes/-n, NOT--body).
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 · 56 lines · 17 tokens per session scan A acdb894c8668
release is a command published in the GitHub repository apetta/agent-xlsx (8 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 17 tokens to every session and 933 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
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.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.