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 skills add ZaxbyHub/opencode-swarm --skill pre-phase-briefinggit clone --depth 1 https://github.com/ZaxbyHub/opencode-swarmWrote 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/zaxbyhub/opencode-swarm/pre-phase-briefing)<a href="https://agentmods.dev/skills/zaxbyhub/opencode-swarm/pre-phase-briefing"><img src="https://agentmods.dev/badge/skills/zaxbyhub/opencode-swarm/pre-phase-briefing/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/zaxbyhub/opencode-swarm/pre-phase-briefing"><img src="https://agentmods.dev/badge/skills/zaxbyhub/opencode-swarm/pre-phase-briefing.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Memory Poisoning · line 35 Skill injects content designed to persist in agent memory or context across interactions. Persistent injection can alter agent behavior long after the initial interaction.Fix: Do not allow untrusted input to persist in agent memory or context. Validate all content before storing and implement memory isolation between sessions.
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 | $0.00033 | $0.01527 |
| Opus 5 | $0.00016 | $0.00763 |
| Sonnet 5 | $0.00007 | $0.00305 |
| Haiku 4.5 | $0.00003 | $0.00153 |
Grade A, and why
pre-phase-briefing 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 3d 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 — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pre Phase Briefing Protocol
This protocol is loaded on demand by the architect runtime. The architect prompt keeps only activation, action, and hard safety constraints; the full execution details live here.
MODE: PRE-PHASE BRIEFING (Required Before Starting Any Phase)
Before creating or resuming any plan, you MUST read the previous phase's retrospective.
Phase 2+ (continuing a multi-phase project):
- Check
.swarm/evidence/retro-{N-1}/evidence.jsonfor the previous phase's retrospective - If it exists: read and internalize
lessons_learnedandtop_rejection_reasons - If it does NOT exist: note this as a process gap, but proceed
- Print a briefing acknowledgment:
→ BRIEFING: Read Phase {N-1} retrospective.
Key lessons: {list 1-3 most relevant lessons}
Applying to Phase {N}: {one sentence on how you'll apply them}
Phase 1 (starting any new project):
- Scan
.swarm/evidence/for anyretro-*bundles from prior projects - If found: review the 1-3 most recent retrospectives for relevant lessons
- Pay special attention to
user_directives— these carry across projects - Print a briefing acknowledgment:
→ BRIEFING: Reviewed {N} historical retrospectives from this workspace.
Relevant lessons: {list applicable lessons}
User directives carried forward: {list any persistent directives}
OR if no historical retros exist:
→ BRIEFING: No historical retrospectives found. Starting fresh.
This briefing is a HARD REQUIREMENT for ALL phases. Skipping it is a process violation.
CODEBASE REALITY CHECK (Required Before Speccing or Planning)
Before any spec generation, plan creation, or plan ingestion begins, the Architect must verify the codebase reality of every item the work references. This runs as asynchronous, fanned-out Explorer lanes by default, joined behind a hard settlement gate — never as a single blocking explorer call, and never as fire-and-forget.
1. Enumerate and partition the references (before dispatch). List every referenced item — file, module, function, API, config surface, and behavioral assumption — named or implied by the spec, the user request, or the plan. Partition them into non-overlapping lane assignments. The partition is the contract: no two lanes may share a reference (this prevents duplicated work), and the union of all lanes must cover every referenced item (this prevents gaps). Under-specified lane boundaries are the dominant fan-out failure mode — be explicit about what each lane owns.
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.
- 3d ago Changed · +8 lines bb855e20dfa0
- 10d ago First seen · 87 lines · 33 tokens per session scan A b0261632bc16
pre-phase-briefing is a skill published in the GitHub repository ZaxbyHub/opencode-swarm (467 stars, last pushed today), licensed MIT. It adds 33 tokens to every session and 1,527 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
armada-gate
Run an evidence-gate checklist for each success criterion in the current phase. Use when checking if a phase is complete before marking it passed.
armada-contract
Co-write an armada contract (REQUIREMENTS.md) one question at a time. Use when drafting or updating a feature contract before implementation.
selftune
Self-improving skills toolkit that watches real agent sessions, detects missed triggers, grades execution quality, and improves skill packages through evals, replay, baselines, review, and post-deploy watch. Use when verifying or publishing a skill, improving instructions or routing, checking skill health, grading…
armada-dispatch
Dispatch subagents in parallel with disjoint file scope. Use when facing 2+ independent tasks, multiple files, or parallel phases. Triggers on: parallelize, dispatch subagents, run in parallel.
armada-voyage-finish
Voyage-finalization ritual. Load at voyage end, dispatch a galleon subagent to rebase, fix TODO PR refs, regen scaffold, push, open/update PR. Triggers on: finish voyage, finalize, rebase, PR.
armada-ledger
Pick the right ledger for a finding. Use when writing defects, adversarial findings, or security findings. Triggers on: ledger, defect, adversarial, security finding, DEF-001, ADV-001, SEC-001.