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 lynxlangya/techne --skill anchor-intakegit clone --depth 1 https://github.com/lynxlangya/techneWrote 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/lynxlangya/techne/anchor-intake)<a href="https://agentmods.dev/skills/lynxlangya/techne/anchor-intake"><img src="https://agentmods.dev/badge/skills/lynxlangya/techne/anchor-intake.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 | $0.00105 | $0.01262 |
| Opus 5 | $0.00053 | $0.00631 |
| Sonnet 5 | $0.00021 | $0.00252 |
| Haiku 4.5 | $0.00011 | $0.00126 |
Grade A, and why
anchor-intake 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 7d 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 — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.
anchor-intake
Force the skipped move before execution: interrogate the written brief against a fixed engineering implementation rubric, then plan only after gaps and weak assumptions are visible.
Trigger Check
Use this skill when the user provides a substantial written engineering implementation brief: a ticket, PRD, design note, or task brief with enough text to interrogate before work starts.
Do not use it for a bare one-line request, an already precise command, a
marketing brief, research proposal, prose draft, code diff review, bug fix, or
implementation execution. For unsupported or too-thin artifacts, self-eject in
one sentence and write no .techne/plan/<slug> output. If a captured artifact
later proves unsupported, use finalize --unscopable --reason ....
Boundary test: can you point to a user-authored written artifact and ask whether
it names the engineering goal, users, measurable success threshold, scope,
non-goals, inputs, data sources, dependencies, constraints, and acceptance
method? If yes, use anchor-intake. If no, eject or ask for the brief first.
Forced Procedure
- Capture the brief. Save the user-authored artifact verbatim. Run:
python3 skills/anchor-intake/scripts/intake_gate.py init --project <root> --plan <slug> --brief-file <path>. - Read the brief in full. Do not fill the rubric from memory or from the user's surrounding chat if the value is not in the captured brief.
- Account every fixed rubric element. For each of the ten elements, write
one disposition in
.techne/plan/<slug>/intake.json:presentwith citation andvalueItems,present-weakwith citation and a dependent question, orgapwith a question or visiblemodelDefault. - Surface traps and conflicts. Add span-anchored
solution-as-goalandcontradictionfindings whenever the brief implies them. Contradictions need two verified spans. - Ask only dependent questions. Every question must resolve an element or
finding and carry a
planDelta. Weak/gap questions must reference the weak span/value or the missing element label. - Author intent-level steps. Steps are not execution yet. Each step needs an
id,dependsOnAssumptions,dependsOnSteps,verifiableOutcome, and at least one terminal step reachable from a root step. - Check and repair. Run:
python3 skills/anchor-intake/scripts/intake_gate.py check --project <root> --plan <slug>. Fix structural failures by doing the missing intake work, not by padding JSON. - Finalize. Run:
python3 skills/anchor-intake/scripts/intake_gate.py finalize --project <root> --plan <slug>. Relay the generatedintakeReport.jsonto the user, especially gaps, weak elements, questions, solution-as-goal findings, contradictions, and warnings.
What ships with it
5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 7d ago First seen · 123 lines · 105 tokens per session scan A e9722661b80d
anchor-intake is a skill published in the GitHub repository lynxlangya/techne (105 stars, last pushed 2mo ago), licensed MIT. It adds 105 tokens to every session and 1,262 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 2026-08-30.
Other skills, from other repositories
go-testing
Trigger: Go tests, go test coverage, Bubbletea teatest, golden files. Apply focused Go testing patterns.
requirements-authoring
To author, update, and validate functional/non-functional requirements as atomic units with user approval.
specflow-use
To connect Rosetta with Grid Dynamics SpecFlow MCP; only when SpecFlow is mentioned and the MCP is installed.
ijfw-workflow
Use when the user says: 'build', 'create', 'plan', 'new project', 'brainstorm', 'design', 'UI', 'website', 'dashboard', 'app', 'help me build', 'launch', 'book', 'campaign', or anything project-level. Skill body decides Quick vs Deep path.
ijfw-plan
Use when the user says 'plan this', 'plan it', 'make a plan', 'let's plan', 'draft a plan', 'how should we tackle this', 'break this down', or invokes '/ijfw-plan'. Produces a falsifiable PLAN.md (software, book, campaign, design, research) with task breakdown, dependency wave-table, and success criteria — gated by…
ijfw-writing-skills
Authoring discipline for new IJFW skills. Use when creating a new skill, writing a skill, making a skill that does X, or asked to add a skill. Trigger: create a new skill, write a skill, new skill, make me a skill, skill that does, /ijfw-writing-skills.