Borrowing it
Nothing to install: this file belongs to bredmond1019/claude-sdk-rs. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/bredmond1019/claude-sdk-rs/main/.agents/skills/commit-in-this-fleet/SKILL.mdgit clone --depth 1 https://github.com/bredmond1019/claude-sdk-rsWrote 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/skills/bredmond1019/claude-sdk-rs/commit-in-this-fleet)<a href="https://agentmods.dev/skills/bredmond1019/claude-sdk-rs/commit-in-this-fleet"><img src="https://agentmods.dev/badge/skills/bredmond1019/claude-sdk-rs/commit-in-this-fleet/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/bredmond1019/claude-sdk-rs/commit-in-this-fleet"><img src="https://agentmods.dev/badge/skills/bredmond1019/claude-sdk-rs/commit-in-this-fleet.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00117 | $0.01408 |
| Opus 5.5 | $0.00047 | $0.00563 |
| Sonnet 5.5 | $0.00023 | $0.00282 |
| Haiku 4.5 | $0.00012 | $0.00141 |
Grade A, and why
commit-in-this-fleet 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 11d 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 — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Committing in this fleet
Paths below are relative to the brain root — the directory containing
brain.toml, found by walking up from wherever you are. This skill is synced into every repo, so a repo-relative link would be wrong in most of them.
Committing here is not ordinary git. One repo owns every planning/ directory in the fleet, and
several agents write to it at once. The default git verbs are wrong by construction.
The one fact everything else follows from
Every planning/ dir — including every core/<repo>/planning — is a symlink into
core/_planning/<repo>/, tracked by the single HQ repo. Check it and see:
git -C core/bastion/planning rev-parse --show-toplevel # -> agentic-portfolio, NOT bastion
So a sub-repo working tree spans two git repos: the repo's own files, and HQ's planning vault.
git status in the sub-repo shows you one of them. That is the whole trap.
The rules
1. Never git add -A, git add ., git reset, or git stash here
Not style — these stage the whole index, which includes any other session's in-flight work in the
shared vault. This has happened repeatedly and is recorded as a fleet trap
(bastion-web:emit-state-rewrites-sibling-repos): one lane's emit-state run modified
core/_planning/bastion/state.json, core/_planning/engine-rs/state.json, README.md and
client/_planning/brazilianportugui/status.md, several carrying other sessions' uncommitted work —
a new block, a dependency-edge removal, hand-written focus prose. A bare git add -A after that
sweeps all of it into your commit.
Always commit with an explicit pathspec:
git commit -o <path1> <path2> -m "..."
2. -o commits only ALREADY-TRACKED changes under those paths
This is the part that looks like it worked and did not. Measured behaviour:
| Situation | What happens |
|---|---|
| Path has tracked modifications | Committed. Correct. |
| Path contains new, untracked files | They are not committed. No error if some other tracked file matched the same pathspec — the commit succeeds and looks complete. |
| No tracked file matches the pathspec at all | error: pathspec '<p>' did not match any file(s) known to git and nothing is committed — not even the other paths on the same command line. |
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.
- 11d ago First seen · 112 lines · 117 tokens per session scan A 7906b88aae7b
commit-in-this-fleet is a skill published in the GitHub repository bredmond1019/claude-sdk-rs (23 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 117 tokens to every session and 1,408 once invoked, about $0.0005 per session on Opus 5.5. 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 2026-10-26.
commit-in-this-fleet compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| commit-in-this-fleetbredmond1019/claude-sdk-rs | Skill | 23 | 1mo ago | Apache-2.0 | A | 117 | Claude Code, Codex |
| create-prprisma/orm | Skill | 48k | yesterday | Apache-2.0 | A | 48 | Claude Code, Codex |
| git-commitThinkInAIXYZ/deepchat | Skill | 6.4k | yesterday | Apache-2.0 | A | 15 | Claude Code, Codex |
| repo-syncdavidondrej/skills | Skill | 4.3k | 3d ago | MIT | A | 25 | Claude Code, Codex |
| engineer-bot-opsmakecindy/cindy | Skill | 9.3k | today | Apache-2.0 | A | 57 | Claude Code, Codex |
| mcore-split-prNVIDIA/skills | Skill | 3.9k | yesterday | Apache-2.0 | A | 25 | Claude Code |
| contributingHugoRCD/evlog | Skill | 1.9k | 12d ago | MIT | A | 68 | Claude Code, Codex |