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 skills add Langerrr/zforge --skill template-conventionsgit clone --depth 1 https://github.com/Langerrr/zforgeWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/langerrr/zforge/template-conventions)<a href="https://agentmods.dev/skills/langerrr/zforge/template-conventions"><img src="https://agentmods.dev/badge/skills/langerrr/zforge/template-conventions/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/langerrr/zforge/template-conventions"><img src="https://agentmods.dev/badge/skills/langerrr/zforge/template-conventions.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What 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 5.1 | $0.00107 | $0.01870 |
| Opus 5.5 | $0.00043 | $0.00748 |
| Sonnet 5.5 | $0.00021 | $0.00374 |
| Haiku 4.5 | $0.00011 | $0.00187 |
Grade A, and why
template-conventions 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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Zforge Template Conventions
Features are documented in docs/{feature_name}/, snake_case.
Core files
Always created by the zforge plan workflow:
| File | Owner | Purpose |
|---|---|---|
00_design_spec.md |
Planner | Problem, actors, requirements, boundary, acceptance vocabulary |
01_context.md |
Planner | Doc Map, key decisions, open questions with owner and method |
02_plan.md |
Planner | Technical plan, phase decomposition, Verification Matrix, environment assumptions, invariants |
discussion.md |
Planner | Reasoning generated during planning — written while thinking, not after |
decision_review.md |
Planner appends · user adjudicates | Decisions made without blocking, awaiting review |
05_progress_overview.md |
Planner only | Phase status, standing flags |
05_progress/05_XX_*.md |
One agent each | Per-phase contract, evidence, decisions, work log |
session_log.md |
Planner | Which sessions touched this feature, and how they ended |
Created when the feature needs them, never as empty placeholders:
| File | When |
|---|---|
| Core patterns doc | The feature changes data models, abstractions or architectural patterns. Without it agents follow the checklist and write structurally wrong code |
03_integration_summary.md, 04_integration_plan.md |
The plan spans backend and frontend |
07_harness_conventions.md |
A phase learns something about how the project is run and observed that a later phase would otherwise pay for again |
05_progress/review.md |
The zforge review workflow has findings |
06_post_deployment.md |
At completion |
08_configuration.md, 09_troubleshooting.md |
Config or gotchas emerge |
10_–12_refactor_* |
The task is a refactoring rather than a new feature |
.zforge-retro/*.md |
The zforge retro workflow is invoked |
Numbering
00–02 and the 05 family have fixed prefixes. Everything else is named for what it is and numbered by creation order in whatever slot is free — the name carries the identity, the number only sorts. Register every document in the Doc Map in 01_context.md with its purpose and which phases it binds.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 1mo ago Changed 86dee36176ec
- 1mo ago Changed e1d894ec6963
- 1mo ago Changed · +2 lines 5442416fcb81
- 1mo ago First seen · 104 lines · 107 tokens per session scan A 282ae88d835b
template-conventions is a skill published in the GitHub repository Langerrr/zforge (10 stars, last pushed 1mo ago), licensed MIT. It adds 107 tokens to every session and 1,870 once invoked, about $0.0004 per session on Opus 5.5. 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 skills, from other repositories
qa
QA testing — browse like a real user, document bugs, report only. Never fixes.
brooks-sweep
Full-sweep mode: runs a unified analysis across all quality dimensions — code decay, architecture, tech debt, and test quality — then applies fixes directly to the codebase. Safe changes are auto-applied; risky changes are confirmed before execution. Drawing on twelve classic engineering books. Triggers when: user…
brooks-test
Test quality review drawing on twelve classic engineering books — with primary focus on xUnit Test Patterns, The Art of Unit Testing, How Google Tests Software, and Working Effectively with Legacy Code — that diagnoses structural problems in an existing test suite: brittleness, mock abuse, coverage illusions, slow…
crap-analyzer
Use to produce a risk-based refactor + test plan for recently-changed code on a diff/branch/PR by computing CRAP (complexity × untested) on changed methods. Multi-language — TypeScript, JavaScript, Python, Java, Kotlin, Go, Ruby, C#, Rust, PHP — auto-discovers how the repo generates coverage. Triggers …
pre-pr-audit
Pre-PR confidence audit with 5-dimension scoring. Use when: final check before commit/push/PR, evaluating PR readiness, assessing test quality + risk + coverage holistically. Triggers: pre-pr, readiness check, confidence audit, final verification, ready to PR, how confident. Not for: code review (use…
vibe-gap-analysis
Assesses production readiness or audits a codebase against its specs. Supports quick static mode, deep 17-dimension audit, or single-dimension focus. Use before a production launch, after a major refactor, when inheriting a codebase, or when someone asks how done the project is.