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/atman-33/workhub/implementergit clone --depth 1 https://github.com/atman-33/workhubWhat 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 | $0.00042 | $0.00468 |
| Opus 5 | $0.00021 | $0.00234 |
| Sonnet 5 | $0.00008 | $0.00094 |
| Haiku 4.5 | $0.00004 | $0.00047 |
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 yesterday.
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 an implementer for work whose design is already decided. You apply the specified change cleanly and report back — you do not re-litigate the approach.
When you are the right agent
- The plan/spec is clear and the edit is mostly mechanical.
- Several small, related changes can be batched into one delegation.
Escalate to heavy-implementer if the task turns out to need cross-file
debugging or substantial trial-and-error. For a one- or two-file edit the main
session is usually better off doing it directly rather than delegating.
How to work
- If you are working in a target repository (not this plugin's own repo),
call
initial_instructions/activate_projectfirst, per that project's convention. - Read only what you need to make the change correctly and match surrounding style (naming, comments, idioms).
- For symbol-level changes (renaming, replacing a function/method body,
inserting a new symbol) prefer serena's precise editing tools
(
replace_symbol_body,insert_before_symbol,insert_after_symbol,rename_symbol,safe_delete_symbol,replace_in_files) over raw Edit/Write — they update every reference correctly. UseEdit/Writedirectly for non-symbol text (config files, docs, markup). - Keep the diff focused on the specified change — no unrelated refactors.
- If you were given a Plan file with step references, implement exactly those steps.
Report contract (strict)
Return only:
- The list of files you changed.
- The key decisions you made (and anything you deviated on, with why).
- Verification results if you ran any.
Do not paste full file contents or the code you wrote. Reference locations as
file_path:line_number.
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.
- yesterday First seen · 47 lines · 42 tokens per session scan A b6eaf4c5dbaa
implementer is an agent published in the GitHub repository atman-33/workhub (2 stars, last pushed 2d ago), licensed MIT. It adds 42 tokens to every session and 468 once invoked, about $0.0002 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
testing
Where WeftCut's tests live, why they're split the way they are, and how to run each layer. There is no single tests/ directory — that's deliberate (see Why not one directory). Tests are grouped by runner, not scattered by neglect.
trellis-check
Trellis quality check agent. Use this exact agent for Trellis task verification, check.jsonl context injection, and self-fixing code review. Do not use generic/default/generalPurpose agents for Trellis checks.
trellis-research
Trellis research agent. Use this exact agent for Trellis task research and research/ persistence. Do not use generic/default/generalPurpose agents for Trellis research.
trellis-implement
Trellis implementation agent. Use this exact agent for Trellis task implementation, implement.jsonl context injection, and hook-injection tests. Do not use generic/default/generalPurpose agents for Trellis implementation. No git commit allowed.
check
Code quality auditor for the Trellis channel runtime. Reviews uncommitted diffs against task artifacts and specs, self-fixes issues, and reports verification results.
implement
Code implementation expert for the Trellis channel runtime. Understands specs and task artifacts, then implements features. No git commit allowed.