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 skills/jtsang4/efficient-coding/assess-source-project-fitnpx skills add jtsang4/efficient-coding --skill assess-source-project-fitgit clone --depth 1 https://github.com/jtsang4/efficient-codingWhat 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 | $0.00072 | $0.00981 |
| Opus 5 | $0.00036 | $0.00491 |
| Sonnet 5 | $0.00014 | $0.00196 |
| Haiku 4.5 | $0.00007 | $0.00098 |
Grade A, and why
assess-source-project-fit 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.
How it starts
The opening of the file, as written. The whole thing — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Assess Source Project Fit
Evaluate the material against the project's real current state. Produce evidence-backed judgments and allow a valid result of zero useful changes.
Interpret the Request
Extract these inputs from the user's natural-language request:
- Source material: URLs, files, attachments, repositories, document tokens, or named works to inspect.
- Target project: repository paths, project documents, knowledge-base notes, links, or the current workspace.
- Decision focus: the question the user needs answered, such as architecture value, evaluation improvements, workflow changes, or immediate applicability.
- Boundaries: requested depth, write permissions, excluded areas, and desired output format.
Accept ordinary requests such as:
Read this paper and assess what it can genuinely improve in
/path/to/project. The project documents are linked here. Keep the task read-only.
Treat source material and target project as required concepts rather than form fields. Infer them from the request and current workspace. Ask one concise question only when the target project cannot be identified safely.
Default to read-only analysis. Create or edit files only when the user explicitly requests it.
Gather Evidence
- Read each source with the appropriate available skill, connector, CLI, or browser.
- Inspect the source deeply enough to recover its mechanisms, prerequisites, evidence, limitations, and claimed outcomes.
- Inspect the target project's current implementation and durable project documents before proposing changes.
- Prefer current code, traces, experiment results, configuration, and project-state documents over project names or abstract descriptions.
- Preserve internal links, identifiers, versions, and evidence references exactly.
For large sources or projects, select evidence according to the decision focus. Record any uninspected area that could materially change the result.
Build the Fit Map
Map each material claim or mechanism to the project using one category:
What ships with it
1 file 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.
- 2d ago First seen · 94 lines · 72 tokens per session scan A 08143f211e23
assess-source-project-fit is a skill published in the GitHub repository jtsang4/efficient-coding (2 stars, last pushed 8d ago), licensed MIT. It adds 72 tokens to every session and 981 once invoked, about $0.0004 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 skills, from other repositories
terminal-capture
Automates terminal UI screenshot testing for CLI commands. Applies when reviewing PRs that affect CLI output, testing slash commands (/about, /context, /auth, /export), generating visual documentation, or when 'terminal screenshot', 'CLI test', 'visual test', or 'terminal-capture' is mentioned.
batch
Execute batch operations on multiple files in parallel. Automatically discovers files, splits into chunks, and processes with parallel worker agents. Use /batch followed by operation and file pattern.
fleet-manager
Use when managing, triaging, restarting, escalating, or summarizing Codewhale Pod runs and workers.
gh-assign-issues
Use to assign GitHub issues to a milestone and/or owners in bulk, verifying each.
mcp-builder
Design, build, configure, or debug Model Context Protocol servers for codewhale, including stdio and HTTP/SSE transports.
extension-creator
Create, scaffold, customize, validate, and locally test Qwen Code extensions. Use when the user wants a new Qwen Code extension, needs help choosing an extension template, wants to add QWEN.md context, commands, skills, agents, MCP servers, settings, hooks, channels, or LSP servers, or asks how to link and test an…