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 commands/vrennat/developersdevelopers/trimgit clone --depth 1 https://github.com/vrennat/developersDevelopersWhat 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 | $0.00571 |
| Opus 5 | $0.00030 | $0.00285 |
| Sonnet 5 | $0.00012 | $0.00114 |
| Haiku 4.5 | $0.00006 | $0.00057 |
Grade A, and why
trim 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.
How it starts
The opening of the file, as written. The whole thing — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/trim
A review with exactly one question: what can be removed? Correctness, security, and style are out of scope — those belong to brutal-code-reviewer (architecture) and adversarial-reviewer (break-it). /trim hunts the opposite failure: code that works but should not exist. Over-engineering, dead flexibility, reinvented standard library, speculative generality.
Scope
Default target is the working change: git diff, staged, and untracked files. Given a path (/trim src/foo.ts or a directory), review that instead.
What to flag
| Tag | Finding |
|---|---|
delete |
Dead code, unused export, unreachable branch, a wrapper that only forwards. |
stdlib |
Hand-rolled logic the language's standard library already does (date math, dedupe, deep clone, clamp). |
native |
A dependency or helper replaceable by a built-in platform feature. |
yagni |
Flexibility, config, or abstraction with one caller and no second on the horizon. |
shrink |
Works, but says in N lines what 1-2 would; collapse it. |
Output
One line per finding, nothing more per finding:
<file>:<line> — <tag> <what>. <replacement>.
Order by impact, most lines saved first. Then a single closing line:
net: -<N> lines possible.
<N> is the summed lines the findings would remove; when uncertain, undercount. If there is genuinely nothing to cut, output exactly:
Lean already. Ship.
Rules
- Every finding names a concrete replacement, not "consider simplifying."
- Flag only what is safe to remove or shrink without changing behavior. A deletion that alters behavior is a correctness call — out of scope.
- No praise, no preamble, no "overall this looks good." Findings and the closing line only.
Example
src/util/dates.ts:14 — stdlib hand-rolled day-diff loop. Use (b - a) / 86400000.
src/api/client.ts:33 — yagni RetryStrategy interface, one impl. Inline the loop.
src/hand/sort.ts:8 — delete unused compareLegacy export. Remove.
net: -41 lines possible.
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 · 58 lines · 59 tokens per session scan A 690e0547cce3
trim is a command published in the GitHub repository vrennat/developersDevelopers (2 stars, last pushed 1mo ago), licensed MIT. It adds 59 tokens to every session and 571 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 commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.