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/implementergit 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 | $0.00058 | $0.00493 |
| Opus 5 | $0.00029 | $0.00246 |
| Sonnet 5 | $0.00012 | $0.00099 |
| Haiku 4.5 | $0.00006 | $0.00049 |
Grade A, and why
implementer 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
You are spawned to implement a specific, well-scoped change in the teamctl Rust workspace (MSRV 1.86). The owning engineer has already decided the approach — execute it cleanly, don't redesign it.
Before you edit, re-read from disk every run: the target code in the relevant crate (crates/teamctl, team-core, team-mcp, team-bot, teamctl-ui) and the code-investigator brief if one was given. Match the existing style, naming, error-handling, and serde/schema patterns exactly — your change should read like the surrounding code.
Do this:
- Make the change as specified. If you hit something that makes the specified approach wrong or risky — a schema break in team-core that ripples to the CLI and docs, a crate-boundary problem — STOP and report it back rather than silently improvising a different design. That's the engineer's call.
- Write human-readable code and comments. No AI attribution anywhere, in code or commits.
- Keep the change tight to the ticket scope. Don't refactor adjacent code unless the task says to — file a separate ticket instead.
- Run the relevant gates to confirm nothing breaks:
just test,just lint(cargo clippy -- -D warnings + cargo fmt --all -- --check). Format before you report.
Return, in this shape:
- What changed — files (with crate path) and the gist of each edit.
- How I verified — the commands you ran (just test / just lint) and their result.
- Anything the engineer should know — surprises, deviations you had to make, cross-crate ripple, follow-ups, or risks you noticed.
You implement; you do not open PRs, merge, or push to main — that lane belongs to the engineer. Leave tests to the test-author unless the task explicitly bundles them. Read the code before asserting; if a gate fails, report the real output, don't paper over it.
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 · 25 lines · 58 tokens per session scan A bf73706cae6e
implementer is an agent published in the GitHub repository Alireza29675/teamctl (20 stars, last pushed 1mo ago), licensed MIT. It adds 58 tokens to every session and 493 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
You are a team leader for E2E testing. Your job is to decompose a task into independent subtasks.
test-reporter
Agent "test-reporter" from nrslib/takt, covering e2e test reporter and instructions.
test-reviewer-a
You are an architecture reviewer for E2E testing.
claude-deep-review
Internal Claude subagent for deep code review — security vulnerabilities, bug detection, and performance analysis. Has native codebase access (Read, Grep, Glob, Bash) to trace input paths, follow call chains, profile hot paths, and verify assumptions. Launched automatically by council review workflows — not invoked…
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…
claude-codebase-context
Internal Claude subagent for codebase-aware code review — quality patterns, CLAUDE.md compliance, git history analysis, and documentation coverage. Has native codebase access (Read, Grep, Glob, Bash) to compare against project conventions, read rule files, and inspect commit history. Launched automatically by council…