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/.squad/skills/team-memory-maintenance/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/team-memory-maintenance)<a href="https://agentmods.dev/skills/bradygaster/squad/team-memory-maintenance"><img src="https://agentmods.dev/badge/skills/bradygaster/squad/team-memory-maintenance/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/team-memory-maintenance"><img src="https://agentmods.dev/badge/skills/bradygaster/squad/team-memory-maintenance.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 | $0.00017 | $0.00392 |
| Opus 5.5 | $0.00007 | $0.00157 |
| Sonnet 5.5 | $0.00003 | $0.00078 |
| Haiku 4.5 | $0.00002 | $0.00039 |
Grade A, and why
team-memory-maintenance 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.
What it actually says
Team Memory Maintenance
Use this skill only for accepted durable decisions. The current Scribe role does not maintain session logs, orchestration logs, specialist histories, onboarding records, or general team memory.
Scope
- Allowed targets:
.squad/decisions/inbox/and.squad/decisions.md. - Use the active state backend for mutable Squad state.
- Preserve decision authorship, rationale, and accepted scope.
- Use archival-integrity procedures whenever accepted records are moved or compacted.
Procedure
- Resolve the supplied team root and configured state backend.
- List and read every candidate inbox entry before acting.
- Merge only decisions that have explicit acceptance evidence.
- Deduplicate exact decision headings without rewriting unrelated decisions.
- Normalize nested headings while preserving relative hierarchy and fenced code blocks.
- Re-read
.squad/decisions.mdand verify the merged content before deleting an inbox entry. - Refetch after deletion and verify the exact inbox entry is absent.
- Stop on any mismatch and report the incomplete operation.
Stop Conditions
- Stop if the team root, active backend, acceptance evidence, or required read-back capability is unavailable.
- Stop if merged content or deletion cannot be verified exactly.
- Do not manufacture a durable record for a tentative request, onboarding observation, or unaccepted recommendation.
Anti-Patterns
- Writing session logs or specialist histories.
- Bypassing the state backend with branch switching, note-ref pushes, resets, or manual persistence.
- Deleting inbox content before verifying the canonical merge.
- Expanding a decision-only maintenance request into product or repository cleanup.
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 Changed · -19 lines · -5 tokens per session d65cbbde9f1d
- 1mo ago First seen · 65 lines · 22 tokens per session scan A 8865fcd3395a
team-memory-maintenance is a skill published in the GitHub repository bradygaster/squad (3,295 stars, last pushed today), licensed MIT. It adds 17 tokens to every session and 392 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
apex-context-management
UTILITY SKILL — Two-mode context-window management. RUNTIME: artifact compression (full/summarized/minimal) for orchestrator and codegen agents. AUDIT: post-mortem analysis of Copilot debug logs (token profiling, redundancy, hand-off gaps) for 11-Context Optimizer. WHEN: "context optimization", "token budget"…
squads-learn
Capture learnings after completing work. Use when finishing a task, fixing a bug, discovering a pattern, or learning something worth remembering for future sessions. Helps build institutional memory.
ce-compound
Document a recently solved problem or durable project vocabulary in docs/solutions/ or CONCEPTS.md. Use when capturing a learning after work.
loadout-remember
Save a durable, cross-project user preference into loadout's global fragments/profiles — or update the fragment it contradicts. Use when the user states lasting guidance that should follow them across projects and agents ("always X", "never Y", "stop doing Z"), especially when it conflicts with guidance the loadout…
end-of-session
Captures session learnings into persistent project memory before closing. Updates task files, project knowledge, and configuration so the next session starts with full context instead of from scratch.
resume
Restore context from a previous session and continue work.