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 rtazima/claude-proj-blueprint --skill intent-markersgit clone --depth 1 https://github.com/rtazima/claude-proj-blueprintWrote 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/rtazima/claude-proj-blueprint/intent-markers)<a href="https://agentmods.dev/skills/rtazima/claude-proj-blueprint/intent-markers"><img src="https://agentmods.dev/badge/skills/rtazima/claude-proj-blueprint/intent-markers/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/rtazima/claude-proj-blueprint/intent-markers"><img src="https://agentmods.dev/badge/skills/rtazima/claude-proj-blueprint/intent-markers.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 | $0.00064 | $0.00773 |
| Opus 5 | $0.00032 | $0.00387 |
| Sonnet 5 | $0.00013 | $0.00155 |
| Haiku 4.5 | $0.00006 | $0.00077 |
Grade A, and why
intent-markers 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 9d 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 — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Intent Markers
Inline annotations that flag code areas needing special attention during review. Grep-able: grep -rn ':PERF:' src/
Marker Reference
| Marker | Meaning | Reviewer action |
|---|---|---|
:PERF: |
Performance-sensitive | Check complexity, allocation, hot paths |
:UNSAFE: |
Safety-critical | Verify justification for bypassing type system, raw pointers, disabled checks |
:SCHEMA: |
Schema-dependent | Check backward compatibility, migration needed? |
:SECURITY: |
Security-sensitive | Auth, encryption, validation, secrets — requires security-auditor review |
:HACK: |
Intentional shortcut | Must have expiration date or issue link. Tracked as tech debt |
:FLAKY: |
Known unreliable | Tests may be flaky, external deps may timeout. Document workaround |
When to ADD markers (writing code)
Add a marker when:
- Code has non-obvious performance implications
- You bypass safety checks or type systems for a reason
- Code depends on a specific DB schema or external contract
- Code handles auth, secrets, encryption, or user input
- You take a deliberate shortcut (always include issue link or date)
- Code depends on unreliable external services or has known flaky behavior
When to CHECK markers (reviewing code)
During code review, search for markers in changed files:
grep -rn ':\(PERF\|UNSAFE\|SCHEMA\|SECURITY\|HACK\|FLAKY\):' src/
Every marker in a diff MUST have a corresponding review comment.
Examples
TypeScript
// :PERF: O(n^2) — acceptable for n < 100 items, refactor if list grows
function findDuplicates(items: Item[]): Item[] {
return items.filter((item, i) => items.findIndex(x => x.id === item.id) !== i);
}
// :SECURITY: Input sanitized before SQL interpolation — parameterized query preferred
const query = `SELECT * FROM users WHERE email = ${sanitize(email)}`;
// :HACK: Workaround for library bug #1234 — remove after v3.0 upgrade
(window as any).__forceRerender = true;
Python
# :UNSAFE: Disabling type check — external API returns untyped dict
result: Any = external_api.fetch() # type: ignore
# :SCHEMA: Depends on users.preferences JSONB column added in migration 042
def get_theme(user: User) -> str:
return user.preferences.get("theme", "light")
# :FLAKY: Stripe webhook delivery is eventually consistent, retry 3x
@retry(max_attempts=3, backoff=2)
def handle_payment_webhook(payload: dict) -> None:
...
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.
- 9d ago First seen · 80 lines · 64 tokens per session scan A 4e8a9e5f48eb
intent-markers is a skill published in the GitHub repository rtazima/claude-proj-blueprint (20 stars, last pushed 3mo ago), licensed MIT. It adds 64 tokens to every session and 773 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
truecourse-analyze
Run TrueCourse architecture analysis on this repository.
mandu-guard-guide
A guide for Mandu Guard, a system that enforces allowed software layers and imports. It also explains six architecture presets, such as Feature-Sliced Design and Clean Architecture.
mandu-guard
Architecture guard system for Mandu. Use when checking layer dependencies, enforcing architecture rules, or validating file locations. Triggers on tasks involving architecture, layers, dependencies, or guard commands.
architecture-governance
Keep code changes conformant to a repo's real, declared architecture using ArchSteer. Use when starting work in an unfamiliar repo, before finishing/committing an architecturally significant change (new dependency, new data access, new external call, new layer), or when asked about a codebase's architecture, layers…
audit
This skill should be used when the user asks to "audit spec coverage", "find uncovered modules", "scan for missing specs", "check wyx coverage", "get spec TODO list", "wyx audit", "wyx", or wants a prioritized list of wyx skill commands for uncovered modules. Scans for coverage gaps, pipeline/sync candidates, and…
go-testing
Trigger: Go tests, go test coverage, Bubbletea teatest, golden files. Apply focused Go testing patterns.