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/seven128/project-tiny-context-harness/context_product_plannpx skills add Seven128/project-tiny-context-harness --skill context_product_plangit clone --depth 1 https://github.com/Seven128/project-tiny-context-harnessWrote 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/seven128/project-tiny-context-harness/context_product_plan)<a href="https://agentmods.dev/skills/seven128/project-tiny-context-harness/context_product_plan"><img src="https://agentmods.dev/badge/skills/seven128/project-tiny-context-harness/context_product_plan.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 5.1 | $0.00102 | $0.00847 |
| Opus 5 | $0.00051 | $0.00424 |
| Sonnet 5 | $0.00020 | $0.00169 |
| Haiku 4.5 | $0.00010 | $0.00085 |
Grade A, and why
context_product_plan 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 5d 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 — 43 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Context Product Plan
Ownership
Own product meaning: goals, users, problem, scope/non-goals, business and user-visible rules, user flows, product feedback, success/acceptance meaning and genuine product decisions. This Skill does not own Product Surface placement, visual Design Authority, generated design resources, technical architecture, implementation, verification authority or a Gate.
Project-specific product behavior belongs in project_context/** and may be specialized by <harnessRoot>/skills/product_plan/SKILL.md. Durable conclusions never live only in the Skill output.
When Long-Task is active, it alone owns Source/Contract lifecycle and Final Gate. This Skill may clarify product meaning for the existing Source/Context, but creates no second plan, requirement ledger, stage or acceptance path.
Workflow
- Read
project_context/global.md,project_context/context.toml, the default area and product owners triggered by the request. Use the default Workflow Contract's bounded high-signal Context search beforeContext Delta. - Establish target users/actors, problem and desired outcome, scope/non-goals, relevant objects/capabilities, main flow and material alternatives, business/user rules, failure/degraded/recovery expectations, success signals and real decision gaps.
- Treat explicit user/product/legal/security/commercial/external constraints as Source. Internally classify each material constraint as Context-covered, requiring Context update, task-local, out of scope or decision-required. Current code reveals implementation; it cannot silently redefine product intent.
- Keep conditions and acceptance concrete enough to be observed through the actual product entry. A representative sample cannot satisfy a declared full-population/all-provider/all-interface/all-platform outcome; unresolved scope is decision-required.
- Route durable information/action/feedback placement, main-versus-drilldown responsibility, screen ownership or cross-surface IA to
context_surface_contract. Provide goals, users, flows, rules and acceptance meaning as inputs; do not compile a Surface Contract here. - Route durable visual identity/tokens/rationale/adopted-target interpretation to
context_uiux_design; new resource generation todesign-resource-authoring; architecture/engineering design tocontext_development_engineer. - Decide exactly one
Context Delta: none|required. Update the smallest product owner before implementation when goals, scope, business/user rules, flow ownership, acceptance semantics or durable rationale change. Local bugs or implementation drift that preserve meaning arenone. - Under the default Workflow Contract, hand implementation to the current Goal and include product conformance in its one current-candidate Contract Conformance. Under Long-Task, project exact non-UI meaning from this product owner into its existing Source/Contract mechanism only—never build a nested Fact ledger or second closure.
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.
- 5d ago First seen · 43 lines · 102 tokens per session scan A f31e6fbfd5c1
context_product_plan is a skill published in the GitHub repository Seven128/project-tiny-context-harness (3 stars, last pushed yesterday), licensed MIT. It adds 102 tokens to every session and 847 once invoked, about $0.0005 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
context-diet
Measure and compact an oversized agent-context file (CLAUDE.md, .cursorrules, AGENTS.md, a system prompt) without losing rules, or safely run reversible bounded, reversible ablation when intentional/aggressive context removal is requested. Triggers: "CLAUDE.md too big", "over the char limit", "context file too large"…
audit-onboarding-proposal
Independently audit a brownfield onboarding transcript, operational map, or exact proposed documentation patch before application. Use when a fresh reviewer must verify an $onboard-repository first pass, distinguish environment-caused Unknowns from reasoning defects, score its safety and evidence gates, or run a…
engineering-wisdom
Provide an explicitly requested, repository-grounded engineering review using contextual heuristics for code clarity, SOLID and design, testing, refactoring, architecture, and professional practice. Use only when the user invokes $engineering-wisdom or explicitly asks for this installed engineering-wisdom pack; do not…
proxmox-full
Complete Proxmox VE hypervisor management via REST API - VMs, containers, snapshots, backups, storage.
red-team-adversarial
Adversarial security and resilience analysis — auto-triggered during /review and /test based on task classification. Provides attack surface analysis, boundary testing, auth bypass attempts, dependency chain attacks, and Beast Mode stress testing.
multi-agent-room
Orchestrate a team of named subagents in shared threads. One orchestrator drives multiple peers with distinct identities; each subagent sees its own inbox and can cross-check findings by posting to a thread the peer is a member of.