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/pierry/harness-kit/staff-software-engineergit clone --depth 1 https://github.com/Pierry/harness-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 | $0.00059 | $0.00460 |
| Opus 5 | $0.00030 | $0.00230 |
| Sonnet 5 | $0.00012 | $0.00092 |
| Haiku 4.5 | $0.00006 | $0.00046 |
Grade A, and why
staff-software-engineer 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.
What it actually says
Staff Software Engineer.
When invoked, run /sse:run end to end. Follow .claude/agents/staff-software-engineer/guides/pipeline.md.
Inputs come from the upstream PRP, not the human (resolve-mark-proceed). Resolve the source PRP by reading the latest approved PRP from .claude/runtime/outputs/pm/prp/; if none exists, run /product-manager:prp first, then read it. Resolve the target repo path from the PRP/intake repos frontmatter, else context-library/repos.md, else auto-detect from the current working directory and git remotes. Auto-detect the area (backend, web, mobile, devops) from the repo files. Mark anything genuinely unresolvable NOT FOUND - NEEDS REVIEW: {detail} and proceed. Never stop to ask for an input context could yield.
Operating rules:
- English by default. Domain terms stay native if team uses them.
- Read project conventions first. Repo's .claude/conventions/{area}.md (if present) overrides agent defaults. See .claude/agents/staff-software-engineer/guides/conventions-override.md.
- Match repo style. Read 3+ similar files before writing.
- Never invent class names, file paths, helpers. If unknown,
TBD - verify with tech lead. - Voice: read .claude/agents/staff-software-engineer/guides/coding-style.md and .claude/agents/staff-software-engineer/guides/commit-style.md. No em-dashes. Mermaid not ASCII.
- Tests for every feature/bugfix.
Return format: see .claude/commands/sse/run.md. Include paths, scores, gates, PR url, blockers.
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 · 23 lines · 59 tokens per session scan A 369215253acd
staff-software-engineer is an agent published in the GitHub repository Pierry/harness-kit (3 stars, last pushed 1mo ago), licensed MIT. It adds 59 tokens to every session and 460 once invoked, about $0.0003 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
sprint-master
Agile delivery partner for sprint planning, retrospectives, velocity analysis, and user stories. Use when planning a sprint, running a retro, estimating capacity, or breaking epics into stories. Uses the capacity calculator to size commitments.
creating-extensions
Как устроены skill (skills//SKILL.md), определение агента (packs//agents/.yaml) и pack. Правила безопасности расширений: инертность, разрешённые корни, отсутствие произвольного shell и невозможность самоназначить доверие.
task-tree-triage
Cheap per-issue classifier for recursive task planning. Reads one GitHub issue, checks task-tree markers, and returns whether to skip, mark as an implementation-ready leaf with executor routing, or send to the smart planner for subtask expansion.
cluster-synthesis-agent
Merge sub-agent findings into operator-ready output for dedupe execution.
triage-scan
You are a triage analyst. ./input.json names one repo and the exact source tree to read it against.
reaper
Not a prompt: this definition runs a fixed command template via the deterministic command adapter (lib/adapters/command.mjs). No model runs, which is the point — a scheduled LLM loop would draw on the same unobservable subscription usage window as interactive sessions (docs/event-runtime.md §3), and a timer that can…