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 jtsang4/efficient-coding --skill assess-source-project-fitgit clone --depth 1 https://github.com/jtsang4/efficient-codingWrote 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/jtsang4/efficient-coding/assess-source-project-fit)<a href="https://agentmods.dev/skills/jtsang4/efficient-coding/assess-source-project-fit"><img src="https://agentmods.dev/badge/skills/jtsang4/efficient-coding/assess-source-project-fit/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/jtsang4/efficient-coding/assess-source-project-fit"><img src="https://agentmods.dev/badge/skills/jtsang4/efficient-coding/assess-source-project-fit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00072 | $0.00981 |
| Opus 5.5 | $0.00029 | $0.00392 |
| Sonnet 5.5 | $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 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 — 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.
- 1mo 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 $0.0003 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
plugin-creator
Create and scaffold plugin directories for Codex with a required .codex-plugin/plugin.json, optional plugin folders/files, valid manifest defaults, and personal-marketplace entries by default. Use when Codex needs to create a new personal plugin, add optional plugin structure, generate or update marketplace entries…
cw-gates
Use before claiming any Codewhale change is done, green, or ready to land: the focused-to-broad verification ladder, the budget checks CI enforces, and the rules for what counts as a passing test.
eval-dataset-design
A guide to creating reliable test sets for AI agents. Each evaluation task includes the request, the simulated user's behaviour, a reset starting state, and a success check that can be independently verified.
memory-system
A guide to giving an AI agent persistent, user-specific memory across conversations. It covers what to remember, how to store it, how to update or compress it, and when to use memory instead of a shared knowledge base.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
interview
Ask one useful structured question at a time only when material product/implementation choices are genuinely missing; remember answers and produce a brief/spec. Discoverable facts should be investigated instead of asked.