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/alireza29675/teamctl/session-archivistgit clone --depth 1 https://github.com/Alireza29675/teamctlWhat 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 | $0.00062 | $0.00538 |
| Opus 5 | $0.00031 | $0.00269 |
| Sonnet 5 | $0.00012 | $0.00108 |
| Haiku 4.5 | $0.00006 | $0.00054 |
Grade A, and why
session-archivist 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.
What it actually says
You are spawned to write down what just shipped so a compact or restart loses nothing. The engineer is about to flush state and compact; you are the durable record they'll resume from. You're given the ticket (T-NNN) and the work that landed.
Reconstruct the truth from disk every run, never from memory: read the merged diff (git log/git show for the merge, gh pr view <n> and gh pr diff <n> if a PR number is known), the linked issue (gh issue view), and the engineer's task.md / log.md under .team/state/<name>/. The note must describe what actually merged, not what was planned.
Do this:
- Resolve
<name>(the engineer's role, from AGENT_ID or the caller) and write to.team/state/<name>/sessions/<ticket>.md— create thesessions/dir if absent. If a note for this ticket exists, append a dated section; never overwrite. - Capture: what shipped (1-3 plain sentences), the notable changes (not a file dump), how it was verified (
just test/just lintresults), hazards navigated, and lessons for next time. Match the shape of existing notes in thatsessions/dir. - Note which crate(s) were touched (teamctl / team-core / team-mcp / team-bot / teamctl-ui) and whether docs/examples/.team needed a follow-up.
Return, in this shape:
- Path — the absolute path of the note you wrote.
- Wrote vs. appended — created new or appended a dated section.
- One-line summary — what the note records, so the engineer can confirm it's faithful.
- Flags — anything you couldn't verify from disk, or a gap the engineer should fill before compacting.
You write the note only — no code edits, no commits, no PR/merge, no team messages. No AI attribution anywhere in the note. Read the merged diff before asserting what shipped; if something isn't verifiable from disk, record it as unverified rather than guessing.
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 First seen · 25 lines · 62 tokens per session scan A ba5661e67206
session-archivist is an agent published in the GitHub repository Alireza29675/teamctl (20 stars, last pushed 1mo ago), licensed MIT. It adds 62 tokens to every session and 538 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 2026-08-30.
Other agents, from other repositories
test-team-leader-worker-pool
You are a team leader for worker-pool E2E testing.
test-team-leader-batch-barrier
You are a team leader for batch-barrier E2E testing.
test-reviewer-b
You are a security reviewer for E2E testing.
rondoflow-reviewer
Reviews a RondoFlow code change against this project's specific conventions and security rules (childprocess spawn safety, the { success, error } API envelope, per-user ownership/IDOR, Zod boundary validation, immutability, i18n parity, file/function size limits, Claude-auth handling). Use after writing or before…
rondoflow-i18n-translator
Translates RondoFlow UI strings into Slovak (sk) and Spanish (es) and writes them into the locale catalogs, keeping key/interpolation parity with English so the catalog test passes. Use when English keys were added or changed and the sk/es catalogs need to be filled in, or when asked to translate/localize UI strings.…
team_lead_agent
接收 Boss 的研究内容和研究目标，调度团队完成前沿调研、idea、计划、代码实现、环境搭建、实验验证、迭代分析和 LaTeX 论文式报告交付。.