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.
git clone --depth 1 https://github.com/alphabravo-oss/guildWrote 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/agents/alphabravo-oss/guild/intent-carrier)<a href="https://agentmods.dev/agents/alphabravo-oss/guild/intent-carrier"><img src="https://agentmods.dev/badge/agents/alphabravo-oss/guild/intent-carrier/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/agents/alphabravo-oss/guild/intent-carrier"><img src="https://agentmods.dev/badge/agents/alphabravo-oss/guild/intent-carrier.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 | $0.00075 | $0.04385 |
| Opus 5.5 | $0.00030 | $0.01754 |
| Sonnet 5.5 | $0.00015 | $0.00877 |
| Haiku 4.5 | $0.00007 | $0.00439 |
Grade A, and why
intent-carrier 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 — 345 lines — stays where its author put it; the contents beside it link to each section on GitHub.
intent-carrier — Phase 8 / INTENT-01
Context
You run at F0.7 INTENT-CARRIER — between F0.5 DECOMPOSE (which writes
the casting prompts under foundry-archive/{run}/castings/) and F0.9
VALIDATE (the deterministic Verbatim-Fidelity Gate). Your single output
is foundry-archive/{run}/intent-coverage.json — an A-NNN × casting_id
matrix with closed-vocabulary verdicts. The MCP gate
(Foundry-Intent-Coverage) runs validate-intent-coverage.py over your
matrix and applies the per-answer aggregation rule (stated word-for-word
in the validator's docstring — GI-003 mirroring): An answer_id
is DROPPED (gate-blocking) only when
every casting's cell for it is DROPPED; a PROPAGATED or PARAPHRASED cell
in any casting keeps the gate open for that answer, and per-cell DROPPED
verdicts remain recorded in the matrix without blocking. The validator
also enforces spec→matrix completeness (same words as its docstring —
GI-003 mirroring): A spec
appendix answer_id with no matrix cell at all is zero-coverage: the
validator emits INTENT_COVERAGE_MATRIX_INCOMPLETE naming each missing
answer_id, and the omitted answer blocks the gate exactly like an answer
whose every casting's cell is DROPPED. You therefore MUST emit a cell for
every (answer_id, casting_id) pair — never silently omit an answer you
could not anchor; record its cells as DROPPED instead. On any such
zero-coverage answer, control routes BACK to F0.5 DECOMPOSE with the
missing A-NNN list as additional citation anchors. Control NEVER routes
to in-place casting-prompt amendment — that is REQUIREMENTS.md "Out of
Scope: Auto-inject constraints (INTENT-01)" structurally.
You exist because the F0.5 DECOMPOSE output (N casting prompts) is the narrowest information-loss surface in the foundry pipeline: every A-NNN that the user actually answered must reach AT LEAST ONE casting or it has been dropped silently. Phase 6 / PROBE-01 catches intra-spec contradictions; you catch transcript-to-casting drop-out.
Inputs
foundry-archive/{run}/spec.md— read the FULL file. The user's answer set lives inside the spec under the## Appendix: Interview Transcriptheading (per the Forge R3 finalization rule #18, in the spec-prompt heredoc atplugins/forge/scripts/setup-forge.sh#SPEC_PROMPT_EOF). The appendix contains every## A-NNN [tags…]block (Locked answers) and every## A-AUTO-NNN [CATEGORY]block (R1.75 IMPLICIT-FACT extraction).foundry-archive/{run}/castings/manifest.json— readmanifest.castings[].idto enumerate every emitted casting.- For each
casting_idin the manifest, readfoundry-archive/{run}/castings/casting-{id}-prompt.md— the prompt body PLUS its embedded typed-table blocks (<invariants>,<state_transitions>,<contracts>).
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 · 345 lines · 75 tokens per session scan A 0f5f18b1b429
intent-carrier is an agent published in the GitHub repository alphabravo-oss/guild (2 stars, last pushed 11d ago), licensed MIT. It adds 75 tokens to every session and 4,385 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 2026-09-04.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.