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 linkpranay-ai/context-engineering-protocol --skill demo-consume-contextgit 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/demo-consume-context)<a href="https://agentmods.dev/skills/linkpranay-ai/context-engineering-protocol/demo-consume-context"><img src="https://agentmods.dev/badge/skills/linkpranay-ai/context-engineering-protocol/demo-consume-context/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/linkpranay-ai/context-engineering-protocol/demo-consume-context"><img src="https://agentmods.dev/badge/skills/linkpranay-ai/context-engineering-protocol/demo-consume-context.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 | $0.00056 | $0.00732 |
| Opus 5 | $0.00028 | $0.00366 |
| Sonnet 5 | $0.00011 | $0.00146 |
| Haiku 4.5 | $0.00006 | $0.00073 |
Grade A, and why
demo-consume-context 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 8d 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 — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Demo: Consuming a Context Package (worked example)
Overview
This is a minimal, from-scratch worked example — not a production skill. It
exists to prove ult-context-generate/CONSUMING-CONTEXT-PACKAGE.md's
consumption contract end-to-end without depending on any larger downstream
skill set. Given a feature name, it produces a one-paragraph "demo note" and
demonstrates every step of the tag loop: discover an existing package (or
proceed without one), cite it while writing, tag the output, and write back
a reverse-index addendum so the package records who consulted it.
Steps
-
Follow
CONSUMING-CONTEXT-PACKAGE.mdsteps 0–3 exactly, using whatever input you were given (a bare feature name is enough — it skips step 0's tag-discovery scan and goes straight to step 1's glob check againstcontexts/). -
Write the demo note to
outputs/demo-notes/<feature-slug>.md— a single paragraph in plain language describing the feature. If a package was loaded in step 1 above, the paragraph must name and paraphrase at least onedecisions_log/decisionsentry orcontext_itemsentry by itssummary, so the loaded content is visibly used, not just fetched. If no package was found, write the paragraph from the feature name alone and say so explicitly in the note's first line. -
Tag the output — per step 9 of the contract, add a
**Context package(s):** <id>@<hash8>line at the top of the note for every package consulted (omit this line entirely if none was). -
Write the reverse-index addendum — per step 9's "Reverse-index addendum" subsection, append a
kind: referenceentry to each consulted package's siblingcontexts/<package-id>_<date>.addenda.yaml(added_by: demo-consume-context,artifact:the note's path). -
State which mode was used, per step 8:
"Context package consulted: <id>@<hash8> (...)", or"No context package found — proceeding without it."
Do NOT use for
Real feature work of any kind — this skill's only output is a one-paragraph
demo note used to exercise the consumption contract. For actual context
package generation, use ult-context-generate. For a real downstream
consumer, follow CONSUMING-CONTEXT-PACKAGE.md directly from whatever skill
is doing the real work, rather than routing through this demo.
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.
- 8d ago First seen · 64 lines · 56 tokens per session scan A c46903ca2587
demo-consume-context is a skill published in the GitHub repository linkpranay-ai/context-engineering-protocol (8 stars, last pushed yesterday), licensed Apache-2.0. It adds 56 tokens to every session and 732 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 2026-08-31.
Other skills, from other repositories
carryover
Use when recalling, saving or curating carryover memory, wikis, playbooks or the Obsidian vault.
bootstrap-llm-synthesis
Construct the LLM synthesis prompt from project surface scan + optional tree-sitter context + optional Q&A answers. Call the LLM. Parse and validate the response into 6-8 structured memory entries with clarity tags and source traceability. Used as Stage 3 of the /gaai:bootstrap pipeline.
memory-delta-triage
Apply three deterministic heuristics to a single memory-delta file to produce a structured verdict block; invoke memory-ingest on ACCEPTED candidates only in validate mode. Activate when Discovery processes a raw memory-delta from contexts/artefacts/memory-deltas/.
memory-reconcile
Scan all memory files, documentation (/docs//.md), and README files (/README.md) for drift, contradictions, and stale references. Produce a reconciliation report for Discovery to action. Activate on demand or via cron.
decision-extraction
Identify and formalize durable product and technical decisions from agent outputs into long-term memory. Activate after Discovery produces artefacts, Delivery resolves trade-offs, or product direction materially changes.
memory-archive-superseded
Migrate a superseded DEC's index rows from active index.md to archive/superseded-decisions.archive.md. Idempotent. Discovery-only — never invoked by daemon delivery. Updates DEC frontmatter as canonical source of truth.