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/linkpranay-ai/context-engineering-protocol/compiling-project-guidelinesnpx skills add linkpranay-ai/context-engineering-protocol --skill compiling-project-guidelinesgit clone --depth 1 https://github.com/linkpranay-ai/context-engineering-protocolWrote 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/linkpranay-ai/context-engineering-protocol/compiling-project-guidelines)<a href="https://agentmods.dev/skills/linkpranay-ai/context-engineering-protocol/compiling-project-guidelines"><img src="https://agentmods.dev/badge/skills/linkpranay-ai/context-engineering-protocol/compiling-project-guidelines.svg" alt="Measured on agentmods" 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 | $0.00043 | $0.05446 |
| Opus 5 | $0.00022 | $0.02723 |
| Sonnet 5 | $0.00009 | $0.01089 |
| Haiku 4.5 | $0.00004 | $0.00545 |
Grade A, and why
compiling-project-guidelines 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 3d 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 — 390 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Compiling Project Guidelines
Overview
Large C/C++/Go/Java codebases (often ~500 KSLOC, sometimes multi-repo) almost always carry their
own design and coding conventions — scattered across CONTRIBUTING.md, .github/instructions/,
architecture docs, PDFs, wiki exports, and tribal knowledge. Project teams will not adopt any
workflow skill that quietly violates those conventions.
This skill is the one-time (and on-demand) compiler: it reads whatever guideline sources a team already has — without asking them to migrate to a new schema or folder convention — and produces a single, predictable, human-readable file that every other skill can cite before it reads, writes, modifies, reviews, or judges project code.
Run this:
- Once, during project setup (
/ult-compile-guidelines) - Again on demand whenever guideline sources change ("update my compiled guidelines — I added
docs/payments-conventions.md")
For multi-repo projects, run it once per repo — scopes are path globs relative to that repo, so no cross-repo machinery is needed.
Output: starter_kit/project_guidelines/COMPILED-GUIDELINES.md — see
the format spec below. This is the only artifact this
skill produces. There is no registry, no schema, no state machine, no decision log file — the
compiled file carries its own provenance and its own conflict-resolution history.
compiled_guidelines (D20 Phase 2, D21 §16.4): the output path above is
the compiled_guidelines path-slot — the registry's only kind: file slot,
resolved via ult-repo-layout/SKILL.md's "Path resolution algorithm (§15.5 +
§16.2)," not a hardcoded path. If /ult-repo-layout init|reconcile has run
for this project, read project_layout.slots.compiled_guidelines.path
(confirmed by its .layout-slots.yaml marker — kind: file, file: COMPILED-GUIDELINES.md); otherwise fall back to the slot's resolved
default — {workspace_root}/cache/project-guidelines/COMPILED-GUIDELINES.md
if layout.workspace_root is set, else
starter_kit/project_guidelines/COMPILED-GUIDELINES.md (unchanged from before
Phase 2). Note the bucket reassignment under workspace_root: this file
re-roots to cache/, not inputs/ — it is a derived artifact, no longer
colocated with the raw starter_kit/project_guidelines/ drop-zone sources
once workspace_root is set. Resolve it once per run and substitute it for
starter_kit/project_guidelines/COMPILED-GUIDELINES.md everywhere it appears
below.
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.
- 3d ago First seen · 390 lines · 43 tokens per session scan A 49f9455e3549
compiling-project-guidelines is a skill published in the GitHub repository linkpranay-ai/context-engineering-protocol (8 stars, last pushed 4d ago), licensed Apache-2.0. It adds 43 tokens to every session and 5,446 once invoked, about $0.0002 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
graft
This repo is indexed by graft/. For ANY task here, whether understanding how something works, finding where code lives, tracing what calls a symbol or what a change breaks, or scoping an edit, get your context from graft before grepping or reading source files.
curate-a-team-library
Use when building a managed team skills library for a real stack. Map work to shelves, browse before curating, write meaningful whyHere notes, and create a starter pack once the first pass is solid.
migrate-skills-between-libraries
Use when moving skills between library workspaces or upgrading from a personal library to a team library. Export from one workspace, import into another.
review-a-skill
Use when evaluating whether a skill belongs in a library. Preview content, check frontmatter, validate structure, and decide whether to keep, curate, or remove.
audit-library-health
Use when checking the overall health of a skills library. Run doctor, validate, check for stale skills, and verify generated docs are in sync.
browse-and-evaluate
Use when exploring the ai-agent-skills catalog to find, compare, and evaluate skills before installing. Always use --fields to limit output size and --dry-run before committing to an install.