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 me-cedric/agent-compass --skill delivery-digestgit clone --depth 1 https://github.com/me-cedric/agent-compassWrote 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/me-cedric/agent-compass/delivery-digest)<a href="https://agentmods.dev/skills/me-cedric/agent-compass/delivery-digest"><img src="https://agentmods.dev/badge/skills/me-cedric/agent-compass/delivery-digest/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/me-cedric/agent-compass/delivery-digest"><img src="https://agentmods.dev/badge/skills/me-cedric/agent-compass/delivery-digest.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 | $0.00045 | $0.00742 |
| Opus 5.5 | $0.00018 | $0.00297 |
| Sonnet 5.5 | $0.00009 | $0.00148 |
| Haiku 4.5 | $0.00005 | $0.00074 |
Grade A, and why
delivery-digest 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 10d 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 — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
delivery-digest
Tell the person who owns the what and the when about the same change that impact-analysis tells to the developers.
The digest gets forwarded to clients, steering committees and wikis. Write it so that forwarding is safe.
Read first
- The change:
git diff --stat <base>...HEADandgit log <base>..HEAD. Ask for the base when it is missing. - The developer note in
{{DELIVERY_DIR}}/impacts/, if it exists. Reuse its findings. - The requirements that the change serves, in
{{OPENSPEC_DIR}}. - The people affected:
{{PERSONAS_FILE}}and{{DELIVERY_DIR}}/assignments.json. - The cost frame, when planning moved:
{{COSTING_DIR}}/*.json.
Translate, do not summarize
Each line answers "so what" for delivery. Group by feature, never by commit or file.
| Instead of | Write |
|---|---|
| A file or module name | The feature or screen that the user sees |
| A refactor | "No visible change. It lowers the risk of X." Or drop it. |
| An endpoint | The action that it enables, and for whom |
| A migration | Whether there is downtime, and whether data is affected |
| A library bump | Only if it changes behavior, cost or a compliance answer |
Redaction
Never write these in the file:
- Secrets, tokens, keys, connection strings, internal hostnames or IPs.
- File paths, function names, stack traces, SQL or code.
- A person's name next to a judgment. Name a profile, such as "Backend developer", unless the user asks for names.
- Internal disagreements, or anything said in confidence.
- Vulnerability detail. Write "a security fix was applied in ".
If you cannot describe a change without one of these, write the business consequence. Add "Technical detail available on request."
Output
Write {{DELIVERY_DIR}}/digests/<YYYY-MM-DD>-<slug>.md.
---
title: <one line that a PO recognizes>
date: <YYYY-MM-DD>
base: <base reference>
audience: product
---
# <title>
**In one sentence:** <text>
## What is now available
## What changed for users
## Scope and planning
| Item | Before | Now | Why |
## Decisions taken
## Waiting on
| What we need | From whom | Blocking | Since |
## Risks and watch points
## Not in this delivery
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.
- 10d ago Changed · -47 lines · -21 tokens per session e269b6b22cf4
- 1mo ago First seen · 129 lines · 66 tokens per session scan A 1e21277012e3
delivery-digest is a skill published in the GitHub repository me-cedric/agent-compass (3 stars, last pushed 4d ago), licensed MIT. It adds 45 tokens to every session and 742 once invoked, about $0.0002 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
paperclip
Use for Paperclip-managed tasks and heartbeats: reading task context, delivering task documents or files, updating completion or blockers, coordinating or delegating work, and following company governance. Includes control plane API operations for assignments, comments, approvals, and routines.
paperclip-task-bridge
Create, comment on, update, and list Paperclip tasks from Hermes using scoped Paperclip API credentials.
parallel-feature-development
Coordinate parallel feature development with file ownership strategies, conflict avoidance rules, and integration patterns for multi-agent implementation. Use this skill when decomposing a large feature into independent work streams, when two or more agents need to implement different layers of the same system…
bazel-build-optimization
Optimize Bazel builds for large-scale monorepos. Use when configuring Bazel, implementing remote execution, or optimizing build performance for enterprise codebases.
process-mapper
Use when a BizOps lead, COO, or process-improvement owner needs to document an end-to-end business process (procurement, employee onboarding, incident handoff, customer-onboarding, claims adjudication) in BPMN-style notation, measure cycle times by stage, surface where work spends most of its time waiting vs. being…
strategic-alignment
Cascades strategy from boardroom to individual contributor. Detects and fixes misalignment between company goals and team execution. Covers strategy articulation, cascade mapping, orphan goal detection, silo identification, communication gap analysis, and realignment protocols. Use when teams are pulling in different…