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 skills/eduardoarantes/agentenv/ship-changesnpx skills add eduardoarantes/agentenv --skill ship-changesgit clone --depth 1 https://github.com/eduardoarantes/agentenvWhat 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 | $0.00061 | $0.01611 |
| Opus 5 | $0.00030 | $0.00805 |
| Sonnet 5 | $0.00012 | $0.00322 |
| Haiku 4.5 | $0.00006 | $0.00161 |
Grade A, and why
ship-changes 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 — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ship changes
Wraps a tested working tree into a published PR. Three phases — audit, commit + push, open PR. Each phase has hard checks; if any fail, stop and report instead of pushing forward.
Phase 1 — audit the diff
Inspect what's about to ship and decide whether documentation needs to move with it.
-
Run the inspection commands in parallel (single tool message, multiple Bash calls):
git status— uncommitted filesgit diff --stat— scope at a glancegit diff(andgit diff --cachedif there's staged content) — actual changesgit log -10 --oneline— recent commit-message style for this repogit branch --show-current— branch you're shipping from
-
Refuse to proceed if:
- Working tree is clean (nothing to ship — say so and stop).
- Files that look sensitive are staged (
.env*,*credentials*,*.pem,*.key, anything matching**/secrets/**). Surface the path and ask the user before continuing.
-
Documentation audit — walk the diff for these signals and report each finding:
Signal in diff Doc that probably needs updating Public API change in crates/*/src/lib.rsor anypub fn/pub structdoc-comments on the changed item; mentions in docs/New CLI subcommand / flag in crates/agentenv-cli/src/main.rsREADME.mdexamples;docs/runbooksNew config field, target name, or capability in crates/agentenv-core/src/config.rsschemas/agentrc.schema.json,.agentrc.example.yaml,CLAUDE.md,docs/platform-standards.mdNew / changed writer or reader path docs/platform-standards.mdper-tool tables,docs/HOOKS.mdNew module under crates/agentenv-core/src/CLAUDE.mddevelopment-areas sectionTest fixtures touching .agentrc.yamlshape.agentrc.example.yamlCargo.tomldep addednothing required, but flag the new dep in the PR body For each finding, check whether the doc already reflects it — grep the doc for the changed identifier / config key. If it does, note "doc already covers it" and move on. If it doesn't, stop and tell the user before committing. List the missing doc updates as a punch list; let the user decide whether to update them now, defer, or proceed without.
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 · 137 lines · 61 tokens per session scan A d7f5ce4e1ad4
ship-changes is a skill published in the GitHub repository eduardoarantes/agentenv (5 stars, last pushed 3mo ago), licensed MIT. It adds 61 tokens to every session and 1,611 once invoked, about $0.0003 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 skills, from other repositories
audit-pass
Run ONE coordinated, ordered, resumable pass over a named target repository: a three-scope inventory first (managed policy read-only, user scope routed as recommendations, project scope), then delegated checks lane by lane, findings persisted per lane so an interrupted run resumes instead of restarting, and one human…
audit-instructions
Audit locally-owned Claude Code instruction surfaces, including CLAUDE.md, .claude/rules, skill bodies, agent definitions, hook instruction text and output styles, for instructions current models no longer need (prior-model workarounds, over-prescriptive scaffolding, stale examples), instructions that misstate Claude…
lanes
Start, restart, stop, and check loop lanes as named background Claude Code sessions seeded from canonical prompt files, the scripted replacement for the manual morning refresh (cancel loop, clear, re-paste the canonical prompt) across N lanes on a machine. start/restart first pull the repo and refresh the plugin…
batch-simplify
Batch-run simplification across changed files, or across an entire repository, grouped by ecosystem and dependency order. Use when: 'batch simplify', 'simplify recent changes', 'simplify everything', 'forgot to run simplify', 'catch up on simplify', 'simplify my branch changes', 'simplify the whole repo', 'simplify…
tidy
Proactively hunt a rotated lane of the codebase for safe structural improvements (Beck's 15 tidyings + a Fowler subset + prose tidyings), apply scope-budgeted edits, and ship one tight structure-only PR per invocation. Use when: 'tidy', 'tidy up', 'boy scout', 'polish', 'small refactors', 'improve gradually', 'clean…
audit-permission-state
Report the Claude Code permission state actually in effect. Discovers every settings scope (managed policy, user-global, project, local, and the pre-v2.1.211 start-directory copy), merges them into the effective allow/ask/deny set with each rule's source and precedence mechanic named, and classifies which allow rules…