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/photostructure/coding-skills/write-clearlynpx skills add photostructure/coding-skills --skill write-clearlygit clone --depth 1 https://github.com/photostructure/coding-skillsWhat 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 | $0.00104 | $0.00900 |
| Opus 5 | $0.00052 | $0.00450 |
| Sonnet 5 | $0.00021 | $0.00180 |
| Haiku 4.5 | $0.00010 | $0.00090 |
Grade A, and why
write-clearly 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 2d 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 — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Write Clearly
Make the intended meaning easy for the intended reader to grasp. Less is more: precise, concise wording respects the reader's time and attention, and every needless word spends both. Preserve facts, uncertainty, necessary detail, and the author's recognizable voice.
Workflow
- Identify the reader, purpose, desired response, format, and tone. State only assumptions that could materially change the result.
- Fix structure before sentences. Lead with the conclusion, request, or action. Keep one topic per paragraph. Use descriptive headings; use lists or tables only when they make real sequences or comparisons easier to scan.
- Apply Orwell's tests:
- Replace stale or mixed figures of speech with fresh wording or literal fact. Test each surviving figure by its literal image: if the picture cannot be drawn ("overarching pillars that undergird", "point a toolkit at a problem"), the words were paired by habit or co-occurrence, not meaning. Fluent phrasing over an incoherent image is the strongest marker of machine-generated prose.
- Prefer the shortest familiar word that is equally exact.
- Cut every word that adds no meaning, tone, or useful rhythm.
- Prefer active voice when it makes the actor and responsibility clearer.
- Replace needless jargon, scientific language, or untranslated foreign terms with an everyday equivalent.
- Break any rule before producing prose that is false, ugly, or inhumane.
- Apply complementary checks:
- Prefer concrete nouns, specific examples, and strong verbs. Turn nominalizations into verbs when that exposes the action.
- Keep necessary technical terms when they are more precise or familiar to the reader; define them on first use when needed.
- Keep subjects near verbs, modifiers near referents, and parallel ideas in parallel form.
- Give each sentence one main thought, but vary sentence and paragraph length enough to avoid a mechanical rhythm.
- Ration signature rhetorical devices: "not X but Y" contrasts, groupings of three, staccato sentence fragments, self-validating asides ("and that matters"), and pet intensifiers such as honestly, actually, and delve. Each is legitimate rhetoric on its own; clustered, they read as machine-generated boilerplate.
- Remove euphemism and abstraction that hide what happened or who is responsible.
- Never gain brevity by changing scope, certainty, causality, intent, or voice.
- Verify the result. Check that the takeaway appears early, actors and actions are unambiguous, and every word earns its place. Read it aloud. For high-stakes public content, ask representative readers to find and paraphrase the key points.
What ships with it
3 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.
- 2d ago First seen · 79 lines · 104 tokens per session scan A f3599867505d
write-clearly is a skill published in the GitHub repository photostructure/coding-skills (3 stars, last pushed 2d ago), licensed MIT. It adds 104 tokens to every session and 900 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
decision-records
Creates, supersedes and validates decision records (ADRs) against the convention a collection already follows, instead of imposing a published one. Use when the user wants to record a decision, write an ADR, supersede an existing decision, audit or lint a decisions folder, check that an ADR index is in sync, or asks…
github-pr-review
Handles PR review comments and feedback resolution. Use when user wants to resolve PR comments, handle review feedback, fix review comments, address PR review, check review status, respond to reviewer, verify PR readiness, review PR comments, analyze review feedback, evaluate PR comments, assess review suggestions, or…
privacy-guard
Prevents private infrastructure details (node hostnames, internal project names, local usernames and personal emails, absolute home paths, private and VPN IP ranges) from leaking into public repositories through commits, PRs, docs or release artifacts. Use when working in a public or soon-to-be-public repo, before…
github-pr-creation
Creates GitHub Pull Requests with automated validation and task tracking. Use when user wants to create PR, open pull request, submit for review, or check if ready for PR. Analyzes commits, validates task completion, generates Conventional Commits title and description, suggests labels. NOTE - for merging existing…
github-pr-merge
Merges GitHub Pull Requests after validating pre-merge checklist. Use when user wants to merge PR, close PR, finalize PR, complete merge, approve and merge, or execute merge. Runs pre-merge validation (tests, lint, CI, comments), confirms with user, merges with proper format, handles post-merge cleanup.
git-commit
Creates git commits following Conventional Commits format with type/scope/subject. Use when user wants to commit changes, create commit, save work, or stage and commit. Enforces project-specific conventions from CLAUDE.md.