bradygaster/squad is a tool that creates a human-directed team of AI development agents inside a project repository through GitHub Copilot. Developers use it to delegate work among persistent specialists such as frontend, backend, testing, and lead agents while retaining responsibility for decisions and review. The catalogue entries are the skills, agents, and instructions that define and coordinate those team members.
Borrowing it
Nothing to install: this file belongs to bradygaster/squad. 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/bradygaster/squad/dev/.copilot/skills/archival-integrity/SKILL.mdgit clone --depth 1 https://github.com/bradygaster/squadWrote 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/bradygaster/squad/archival-integrity)<a href="https://agentmods.dev/skills/bradygaster/squad/archival-integrity"><img src="https://agentmods.dev/badge/skills/bradygaster/squad/archival-integrity/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/bradygaster/squad/archival-integrity"><img src="https://agentmods.dev/badge/skills/bradygaster/squad/archival-integrity.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 | $0.00016 | $0.00591 |
| Opus 5.5 | $0.00006 | $0.00236 |
| Sonnet 5.5 | $0.00003 | $0.00118 |
| Haiku 4.5 | $0.00002 | $0.00059 |
Grade A, and why
archival-integrity 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 1mo 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 — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Context
Use this skill for decision archival, history summarization, or any operation that moves entries between repository state files. A move has two halves: append to the destination, then trim the source. Treat it as data loss prevention, not text cleanup.
Scope
- Activate when moving entries between tracked Squad state files such as decision logs, histories, or inbox merges.
- Allowed targets: tracked repository state files and their designated tracked archives.
- Exclusions: untracked destinations, byte-delta-only validation, and trimming source content before the destination is verified.
- This procedure is scoped to the local state backend unless the active backend exposes governed append, read-back, and trim operations. Runtime-owned orphan or two-layer state is not a valid archival destination; use the backend's state operation instead of editing a checkout copy.
Patterns
- Resolve a destination that is already tracked before writing. If the requested destination is untracked, redirect to a tracked archive or stop.
- Append first, re-read the destination, and prove every moved heading is present.
- Compare entry counts before and after the append. Trim only when the count increased by exactly the selected number of entries.
- Report measured
removed from source / added to destinationcounts. Do not use byte deltas as an integrity signal. - When inserting an inbox body beneath a
###entry, demote its shallowest heading to####while preserving relative levels and fenced-code content. - Prefer
archiveEntries(),prepareInboxBodyForMerge(), andformatArchivalReport()frompackages/squad-sdk/src/state/io/archival.tsover hand-rolled archival logic.
Stop conditions
- Stop if the destination is not already tracked.
- Stop if the appended headings cannot be re-read from the destination.
- Stop if the entry-count increase does not exactly match the selected move set.
- Stop if the active backend is non-local and does not provide governed archival operations.
- Stop if state appears orphaned, split across runtime and checkout layers, or owned by another process without an explicit handoff.
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.
- 1mo ago First seen · 58 lines · 16 tokens per session scan A 9e4f9169f5a2
archival-integrity is a skill published in the GitHub repository bradygaster/squad (3,300 stars, last pushed today), licensed MIT. It adds 16 tokens to every session and 591 once invoked, about $0.0001 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 2026-09-12.
Other skills, from other repositories
setup-husky-dotnet
Use when configuring Git hooks in .NET projects before team commits occur, to enforce commit message standards and code formatting automatically.
ce-commit-push-pr
Commit, push, and open a PR. Use when asked to ship/open a PR, or for PR-description-only flows like writing, rewriting, or describing a PR body.
git-workflow
Essential Git patterns for effective version control, eliminating redundant Git guidance per agent.
commit-conventions
Standards for writing clear and consistent commit messages using Conventional Commits format. Use when making git commits, reviewing commit history, creating pull requests, or when the user asks about commit message formatting, git workflows, or version control best practices.
work-unit-commits
Plan commits as reviewable work units. Trigger: implementation, commit splitting, chained PRs, or keeping tests and docs with code.
atmos-git
Atmos Git and GitOps: git.repositories, clone/pull/status/diff/commit/push/clean, local Git hook shims and hook env vars, signed commits, managed workdirs, fork-PR trust gate (clone gate and posting gate), and auth via identities or github/sts.