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 thiscantbeserious/agent-session-recorder --skill rolesgit clone --depth 1 https://github.com/thiscantbeserious/agent-session-recorderWrote 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/thiscantbeserious/agent-session-recorder/roles)<a href="https://agentmods.dev/skills/thiscantbeserious/agent-session-recorder/roles"><img src="https://agentmods.dev/badge/skills/thiscantbeserious/agent-session-recorder/roles/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/thiscantbeserious/agent-session-recorder/roles"><img src="https://agentmods.dev/badge/skills/thiscantbeserious/agent-session-recorder/roles.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 | $0.00071 | $0.01191 |
| Opus 5 | $0.00036 | $0.00596 |
| Sonnet 5 | $0.00014 | $0.00238 |
| Haiku 4.5 | $0.00007 | $0.00119 |
Grade A, and why
roles 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 9d 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 — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Roles
1. Access pattern
If no role is explicitly assigned, default to references/coordinator.md.
Startup policy:
- If user intent is explicit, skip menu and execute directly:
- Explicit SDLC request -> start coordinator SDLC flow
- Explicit direct question -> stay in Direct Assist
- Explicit
/rolesrequest -> switch to requested role directly - Explicit named role request without
/roles-> ask for confirmation before switching roles
- If user message is simple greeting/small talk, respond naturally first, then offer:
- Start SDLC workflow
- Direct Assist (no SDLC yet)
- For unclear non-trivial requests, offer the two paths without forcing a rigid "pick a number" format.
Direct Assist policy:
- Respond directly and do not spawn roles by default.
- Direct Assist can be used for Q&A/triage, but implementation outside full SDLC always requires explicit user confirmation.
- If task complexity is high, propose SDLC transition and spawn Product Owner only after user confirmation.
- Complexity triggers include:
- Multi-file changes
- Architecture/design decisions
- Unclear acceptance criteria
- Elevated regression risk
Quick implementation loop (inside Direct Assist):
- Only after explicit user confirmation, for small bounded implementation tasks, run a minimal quality loop:
- Spawn Implementer
- Spawn Reviewer (internal)
- Return reviewed result to user
- Mandatory gates:
- Implementer runs tests (at least
cargo test+ targeted tests) - Reviewer reports findings with severity
- Blocking findings are fixed before handoff
- Implementer runs tests (at least
- This loop does not bypass coordinator-managed flow; it is a confirmed fast path within Direct Assist.
/rolesis the only no-confirmation bypass of full SDLC. Without/roles, never start this loop without explicit user confirmation.- Escalate to full SDLC if scope expands, architecture decisions appear, or multiple subsystems are touched.
Deterministic checks policy:
- Use
cargo xtask validate-workflowto enforce role/workflow invariants. - Use
cargo xtask validate-plan --plan .state/<branch>/PLAN.mdbefore parallel implementation. - Use
cargo xtask coordinate-plan --plan .state/<branch>/PLAN.mdto derive dependency-safe spawn batches.
What ships with it
11 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- README.md 9.4 KB
- references/architect.md 3.5 KB
- references/coordinator.md 20 KB
- references/implementer.md 2.5 KB
- references/maintainer.md 3.5 KB
- references/product-owner.md 5.6 KB
- references/reviewer.md 10 KB
- templates/ADR.md 579 B
- templates/PLAN.md 793 B
- templates/REQUIREMENTS.md 457 B
- templates/REVIEW.md 898 B
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.
- 9d ago First seen · 122 lines · 71 tokens per session scan A cdd93e70ecbf
roles is a skill published in the GitHub repository thiscantbeserious/agent-session-recorder (5 stars, last pushed 6mo ago), licensed MIT. It adds 71 tokens to every session and 1,191 once invoked, about $0.0004 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…