Borrowing it
Nothing to install: this file belongs to dgenio/contextweaver. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/dgenio/contextweaver/main/.github/prompts/add-feature.prompt.mdgit clone --depth 1 https://github.com/dgenio/contextweaverWrote 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/commands/dgenio/contextweaver/add-feature)<a href="https://agentmods.dev/commands/dgenio/contextweaver/add-feature"><img src="https://agentmods.dev/badge/commands/dgenio/contextweaver/add-feature/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/commands/dgenio/contextweaver/add-feature"><img src="https://agentmods.dev/badge/commands/dgenio/contextweaver/add-feature.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 | $0.00014 | $0.00536 |
| Opus 5.5 | $0.00006 | $0.00214 |
| Sonnet 5.5 | $0.00003 | $0.00107 |
| Haiku 4.5 | $0.00001 | $0.00054 |
Grade A, and why
add-feature 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 — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Add a Feature
Follow these steps in order. Each step has a clear success criterion.
References
AGENTS.md— module map, hard rules, strong patterns, coding style.github/instructions/context.instructions.md— context engine invariants.github/instructions/routing.instructions.md— routing engine invariants.github/instructions/sensitivity.instructions.md— security-grade sensitivity codedocs/agent-context/invariants.md— hard constraints and forbidden shortcuts
Steps
-
Identify the target module. Consult the module map in
AGENTS.md. If no existing module fits, propose a new one that satisfies the ≤300-line guideline. Success: module path is known. -
Check current module size. Run
wc -l src/contextweaver/<module>.py. If the feature would push a non-exempt module over 300 lines, stop and open a refactor issue first. Success: target module will remain ≤300 lines after the change. -
Add the feature code. Apply coding-style rules from
AGENTS.md:from __future__ import annotations, type hints, Google-style docstrings, noprint()in library code, exceptions fromcontextweaver.exceptionsonly. Success:make lint && make typepass. -
Update
protocols.pyif needed. If the feature introduces a new protocol interface, add it toprotocols.py. Success: no new Protocol defined outsideprotocols.py. -
Add tests. Create or extend
tests/test_<module>.py. Use real in-memory implementations — do not mock internal modules. Usepytest.mark.asynciofor async paths. Success:make testpasses with new tests included. -
Update
CHANGELOG.md. Add a concise entry under## [Unreleased]. Success: entry is present. -
Update agent-facing docs if invariants changed. If the feature changes the pipeline, public API, or conventions, update
AGENTS.mdand/ordocs/agent-context/. Success: docs match code. -
Run
make ciand verify all checks pass.make ciSuccess: all targets (
fmt lint type test example demo) exit 0.
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 · 51 lines · 14 tokens per session scan A eb8aba638be7
add-feature is a command published in the GitHub repository dgenio/contextweaver (9 stars, last pushed 3d ago), licensed Apache-2.0. It adds 14 tokens to every session and 536 once invoked, about $0.0001 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 2026-09-08.
Other commands, from other repositories
enforce.python
Enforce repository-wide compliance with python.instructions.md.
enforce.playwright-python
Enforce repository-wide compliance with playwright-python.instructions.md.
type-coverage
Vérification Couverture des Types Python.
execute-pydantic-ai-prp
Implement a Pydantic AI agent using the PRP file.
package-review
Review the current Python package for best-practice violations — project structure, pyproject.toml, typing, testing, CI/CD, documentation, versioning, API design, packaging, security, and developer experience.
typography
This command is a lookup + decision, not a multi-step build — it doesn't need its own workflow file. If the request grows into "and now build the page using this type system," hand off to page or redesign.