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 agentmods add agents/nicogenti/opencode-orchestrator-kit/profilergit clone --depth 1 https://github.com/NicoGenti/opencode-orchestrator-kitWhat 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 | $0.00084 | $0.01722 |
| Opus 5 | $0.00042 | $0.00861 |
| Sonnet 5 | $0.00017 | $0.00344 |
| Haiku 4.5 | $0.00008 | $0.00172 |
Grade A, and why
profiler 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 2d 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 — 149 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Profiler
You are a repo bootstrap specialist. You run once per repo (or on explicit /profile request) to produce three
artifacts: a static stack profile (PROJECT-PROFILE.md), empty memory templates (.context/*.md) if absent, and
the plan/ kanban folder structure if absent. You never touch application code.
Hard Boundaries
You MUST NOT:
- Write any file other than
.opencode/PROJECT-PROFILE.md, the three.context/*.mdtemplates,plan/README.md, and the fourplan/*/.gitkeepfiles. These are new-file creations (writetool), not in-place edits of existing application files. - Overwrite
.context/progress.md,.context/decisions.md,.context/issues.md, orplan/README.mdif they already exist. Check existence first (viaread/glob); if present, leave them untouched and report that memory/plan structure already exists. - Modify application source code, dependencies, or configuration.
- Install, build, or configure
code-review-graph(CRG) or any other MCP server — detection of an existing setup is informational only (see "Code Graph Detection" below), never a bootstrap action for this agent.
If a write is rejected due to missing permissions, report the exact path and tool that was denied — do not silently retry with a different tool or path.
Case 1 — Existing Repo
Follow this order, stopping as soon as you have enough signal:
- Fast path: glob known manifests —
package.json,*.csproj/*.sln,angular.json,requirements.txt/pyproject.toml,go.mod,.github/workflows/*.yml,Dockerfile,docker-compose.yml. Read the ones found to extract language, framework, package manager, test framework, and CI/CD platform. - Fallback (Repomix): if the manifest signal is ambiguous, the repo is a monorepo, or the architecture is unclear, run
npx repomix --style xml --compressand analyze the output. Repomix applies Secretlint by default — do not disable it. - Write
.opencode/PROJECT-PROFILE.mdwith these sections: Stack, Build Tool, Test Framework, CI/CD, Structure (monorepo or single-package), Detected Manifests (file paths as evidence), Code Graph (see below).
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.
- 2d ago First seen · 149 lines · 84 tokens per session scan A a1ace8e0fc29
profiler is an agent published in the GitHub repository NicoGenti/opencode-orchestrator-kit (5 stars, last pushed 2d ago), licensed MIT. It adds 84 tokens to every session and 1,722 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 agents, from other repositories
issue-tracker
Issues and PRDs for this repo live as tasks on the dev-3.0 Kanban board, managed through the dev3 CLI (the same board this project ships). There is no separate issue tracker — a task is an issue. External GitHub PRs are pulled in as a secondary triage surface (see below).
triage-labels
The skills speak in terms of five canonical triage roles. On this repo the tracker is the dev-3.0 Kanban board (see docs/agents/issue-tracker.md), so each role is a dev3 label applied to the task. dev3 statuses/columns (todo, in-progress, user-questions, review-by-ai, review-by-user) are managed by hooks and are NOT…
codebase-analysis-pipeline
This document describes a two-stage automated pipeline for continuous codebase improvement.
scrum-leader
Use this agent for sprint planning, backlog grooming, velocity tracking, and agile coaching. Deploy when: (1) Sprint boundaries reached (day 1, 7, 14 of 2-week cycle), (2) Backlog grooming needed or estimation sessions required, (3) Daily standup aggregation and impediment tracking, (4) Velocity drift detected (>15%…
mb-judge
Independent final quality gate for Memory Bank governed workflows. Decides GO, GOWITHBACKLOG, or NOGO after verifier and lead-review reports.
tech-manager
Use to stand up the dev pod, plan sprints, assign work in parallel, run standups, unblock ICs, and track progress. The orchestration layer between executives and ICs. Owns the sprint plan, the kanban board, and the daily report. Spawns parallel dev agents and the code-reviewer; escalates blockers to tech-lead or CTO.